Valid HTML 4.0! Valid CSS!
%%% -*-BibTeX-*-
%%% ====================================================================
%%%  BibTeX-file{
%%%     author          = "Nelson H. F. Beebe",
%%%     version         = "1.13",
%%%     date            = "14 October 2017",
%%%     time            = "10:25:21 MDT",
%%%     filename        = "sgml2010.bib",
%%%     address         = "University of Utah
%%%                        Department of Mathematics, 110 LCB
%%%                        155 S 1400 E RM 233
%%%                        Salt Lake City, UT 84112-0090
%%%                        USA",
%%%     telephone       = "+1 801 581 5254",
%%%     FAX             = "+1 801 581 4148",
%%%     URL             = "",
%%%     checksum        = "12106 1566 7266 73095",
%%%     email           = "beebe at, beebe at,
%%%                        beebe at (Internet)",
%%%     codetable       = "ISO/ASCII",
%%%     keywords        = "Audio XmL; BibTeX; bibliography; Cascading
%%%                        Style Sheets (CSS); Channel Definition Format
%%%                        (CDF); Chemical Markup Language (CML);
%%%                        Extensible Markup Language (XML); Extensible
%%%                        Style Language (XSL); Hypertext Markup
%%%                        Language (HTML); Hytime; Mathematical Markup
%%%                        Language (MML); Standard Generalized Markup
%%%                        Language (SGML); VoiceXML; World-Wide Web
%%%                        (WWW)",
%%%     license         = "public domain",
%%%     supported       = "yes",
%%%     docstring       = "This bibliography records publications on
%%%                        SGML (Standard Generalized Markup Language)
%%%                        and descendants, including Channel Definition
%%%                        Format (CDF), Chemical Markup Language (CML),
%%%                        HTML (Hypertext Markup Language) [used on the
%%%                        World-Wide Web], Mathematical Markup Language
%%%                        (MML), VoiceXML, and VRML (Virtual Reality
%%%                        Markup/Modeling Language).  CDF, HTML, MML,
%%%                        and XML are specific SGML Document Type
%%%                        Definitions conforming to the SGML grammar.
%%%                        This bibliography includes publications for
%%%                        years 2010--2019.  The companion
%%%                        bibliographies sgml.bib and sgml2000.bib
%%%                        contain data for earlier years.
%%%                        At version 1.13, the year coverage looks
%%%                        like this:
%%%                             2010 (  28)    2012 (   1)
%%%                             2011 (   0)    2013 (   1)
%%%                             Article:         26
%%%                             Book:             4
%%%                             Total entries:   30
%%%                        These references have been extracted from a
%%%                        very large computer science bibliography
%%%                        collection on in
%%%                        /pub/bibliography to which many people of
%%%                        have contributed.  The snapshot of this
%%%                        collection was taken on 5-May-1994, and it
%%%                        consists of 441 BibTeX files, 2,672,675
%%%                        lines, 205,289 entries, and 6,375
%%%                        <at>String{} abbreviations, occupying
%%%                        94.8MB of disk space.  It was then
%%%                        augmented by data from the ACM Computing
%%%                        Archive CD ROM, the IEEE INSPEC CD ROMs
%%%                        (1989--Sept. 1996), and various
%%%                        Internet-accessible library catalogs,
%%%                        including the OCLC Article1st,
%%%                        BooksInPrint, Contents1st, ERIC, EconLit,
%%%                        GEOBASE, GPO, MEDLINE, PapersFirst,
%%%                        Proceedings, WorldCat databases, the
%%%                        UnCover library database, and the Compendex
%%%                        database.
%%%                        The SGML Web Page provides a reference
%%%                        collection of 1,900 documents and a annotated
%%%                        database of 1,600 citations.  There are also
%%%                        current listings of public-domain and
%%%                        commercial SGML software and resources,
%%%                        academic and commercial products which use
%%%                        SGML, and guides to related markup languages
%%%                        like DSSL and XML.
%%%                        There is an interesting World-Wide Web
%%%                        resource available for SGML at the URL
%%%                        Other resources are available at
%%%                        BibTeX citation tags are uniformly chosen
%%%                        as name:year:abbrev, where name is the
%%%                        family name of the first author or editor,
%%%                        year is a 4-digit number, and abbrev is a
%%%                        3-letter condensation of important title
%%%                        words. Citation tags were automatically
%%%                        generated by software developed for the
%%%                        BibNet Project.
%%%                        In this bibliography, entries are sorted
%%%                        first by ascending year, and within each
%%%                        year, alphabetically by author or editor,
%%%                        and then, if necessary, by the 3-letter
%%%                        abbreviation at the end of the BibTeX
%%%                        citation tag.  `bibsort -byyear' automates
%%%                        the job.  Year order has been chosen to
%%%                        make it easier to identify the most recent
%%%                        work.  Cross-referenced proceedings entries
%%%                        appear at the end, because of a restriction
%%%                        in the current BibTeX.
%%%                        The checksum field above contains a CRC-16
%%%                        checksum as the first value, followed by the
%%%                        equivalent of the standard UNIX wc (word
%%%                        count) utility output of lines, words, and
%%%                        characters.  This is produced by Robert
%%%                        Solovay's checksum utility.",
%%%  }
%%% ====================================================================
  "\input tugboat.def" #
  "\input path.sty" #

%%% ====================================================================
%%% Acknowledgement abbreviations:
@String{ack-nhfb = "Nelson H. F. Beebe,
                    University of Utah,
                    Department of Mathematics, 110 LCB,
                    155 S 1400 E RM 233,
                    Salt Lake City, UT 84112-0090, USA,
                    Tel: +1 801 581 5254,
                    FAX: +1 801 581 4148,
                    e-mail: \path||,
                            \path|| (Internet),
                    URL: \path||"}

%%% ====================================================================
%%% Journal abbreviations:
@String{j-ACTA-INFO = "Acta Informatica"}

@String{j-APPL-MATH-COMP        = "Applied Mathematics and Computation"}

@String{j-CACM                  = "Communications of the ACM"}

@String{j-CCCUJ                 = "C/C++ Users Journal"}

@String{j-COMP-J                = "The Computer Journal"}

@String{j-COMP-NET-AMSTERDAM    = "Computer Networks (Amsterdam, Netherlands:

@String{j-COMP-SURV             = "ACM Computing Surveys"}

@String{j-COMPUT-SCI-ENG        = "Computing in Science and Engineering"}

@String{j-COMPUTER              = "Computer"}

@String{j-COMPUTING             = "Computing"}

@String{j-DDJ                   = "Dr. Dobbs Journal"}

@String{j-FORTRAN-FORUM = "ACM Fortran Forum"}

@String{j-FUT-GEN-COMP-SYS      = "Future Generation Computer Systems"}

@String{j-IBM-SYS-J             = "IBM Systems Journal"}

@String{j-IEEE-DISTRIB-SYST-ONLINE = "IEEE Distributed Systems Online"}

@String{j-INFO-PROC-LETT        = "Information Processing Letters"}

@String{j-INT-J-COMP-PROC-ORIENTAL-LANG = "International Journal of
                                  Computer Processing of Oriental
                                  Languages (IJCPOL)"}

@String{j-INT-J-COMPUT-SYST-SCI-ENG = "International Journal of Computer
                                  Systems Science and Engineering"}

@String{j-J-ACM                 = "Journal of the ACM"}

@String{j-J-CHEM-INFO-COMP-SCI  = "Journal of Chemical Information and Computer

@String{j-J-PAR-DIST-COMP       = "Journal of Parallel and Distributed

@String{j-J-SYST-SOFTW          = "The Journal of Systems and Software"}

@String{j-J-UCS                 = "J.UCS: Journal of Universal Computer

@String{j-JCD                   = "ACM Journal of Computer Documentation"}

@String{j-LECT-NOTES-COMP-SCI   = "Lecture Notes in Computer Science"}

@String{j-LIB-HI-TECH           = "Library Hi Tech"}

@String{j-LINUX-J               = "Linux Journal"}

@String{j-MATH-COMPUT-SCI       = "Mathematics in Computer Science"}

@String{j-MINI-MICRO-SYSTEMS    = "Mini-Micro Systems"}

@String{j-OPER-SYS-REV          = "Operating Systems Review"}

@String{j-SCI-PROG              = "Scientific Programming"}

@String{j-SIAM-J-COMPUT         = "SIAM Journal on Computing"}

@String{j-SIGCSE                = "SIGCSE Bulletin (ACM Special Interest Group
                                  on Computer Science Education)"}

@String{j-SIGMOD                = "SIGMOD Record (ACM Special Interest
                                  Group on Management of Data)"}

@String{j-SIGPLAN               = "ACM SIG{\-}PLAN Notices"}

@String{j-SPE                   = "Soft\-ware\emdash Prac\-tice and Experience"}

@String{j-THEOR-COMP-SCI        = "Theoretical Computer Science"}

@String{j-TISSEC                = "ACM Transactions on Information and System

@String{j-TOCL                  = "ACM Transactions on Computational Logic"}

@String{j-TODS                  = "ACM Transactions on Database Systems"}

@String{j-TOIS                  = "ACM Transactions on Information Systems"}

@String{j-TOIT                  = "ACM Transactions on Internet Technology

@String{j-TOPLAS                = "ACM Transactions on Programming
                                  Languages and Systems"}

@String{j-TWEB                  = "ACM Transactions on the Web (TWEB)"}

@String{j-VLDB-J                = "VLDB Journal: Very Large Data Bases"}

%%% ====================================================================
%%% Publishers and their addresses:
@String{pub-ACM                 = "ACM Press"}

@String{pub-ACM:adr             = "New York, NY, USA"}

@String{pub-AP                  = "Academic Press"}

@String{pub-AP:adr              = "New York, USA"}

@String{pub-APRESS              = "Apress"}

@String{pub-APRESS:adr          = "Berkeley, CA, USA"}

@String{pub-AW                  = "Ad{\-d}i{\-s}on-Wes{\-l}ey"}

@String{pub-AW:adr              = "Reading, MA, USA"}

@String{pub-CMP-BOOKS           = "CMP Books"}

@String{pub-CMP-BOOKS:adr       = "6600 Silacci Way, Gilroy, CA 95020, USA"}

@String{pub-CORIOLIS            = "Coriolis Group Books"}

@String{pub-CORIOLIS:adr        = "Scottsdale, AZ, USA"}

@String{pub-COURSE-TECHNOLOGY   = "Course Technology"}

@String{pub-COURSE-TECHNOLOGY:adr = "Cambridge, MA, USA"}

@String{pub-CRC                 = "CRC Press"}

@String{pub-CRC:adr             = "2000 N.W. Corporate Blvd., Boca Raton, FL
                                  33431-9868, USA"}

@String{pub-HUNGRY-MINDS        = "Hungry Minds"}

@String{pub-HUNGRY-MINDS:adr    = "909 Third Avenue, New York, NY 10022, USA"}

@String{pub-IBM-REDBOOKS        = "IBM Redbooks"}

@String{pub-IBM-REDBOOKS:adr    = "11400 Burnet Road, Austin, TX 78758-3493,

@String{pub-IDG                 = "IDG Books"}

@String{pub-IDG:adr             = "San Mateo, CA, USA"}

@String{pub-IRWIN-MCGRAW-HILL   = "Irwin\slash McGraw Hill"}

@String{pub-IRWIN-MCGRAW-HILL:adr = "Boston, MA, USA"}

@String{pub-ISO                 = "International Organization for

@String{pub-ISO:adr             = "Geneva, Switzerland"}

@String{pub-ITP                 = "International Thomson Publishing"}

@String{pub-ITP:adr             = "5101 Madison Road, Cincinnati, OH
                                  45227, USA; Bonn, Germany"}

@String{pub-MANNING             = "Manning Publications"}

@String{pub-MANNING:adr         = "Greenwich, CT, USA"}

@String{pub-MCGRAW-HILL         = "Mc{\-}Graw-Hill"}

@String{pub-MCGRAW-HILL:adr     = "New York, NY, USA"}

@String{pub-MICROSOFT           = "Microsoft Press"}

@String{pub-MICROSOFT:adr       = "Bellevue, WA, USA"}

@String{pub-MORGAN-KAUFMANN     = "Morgan Kaufmann Publishers"}

@String{pub-MORGAN-KAUFMANN:adr = "Los Altos, CA 94022, USA"}

@String{pub-MT                  = "M\&T Books"}

@String{pub-MT:adr              = "M\&T Publishing, Inc., 501 Galveston Drive,
                                    Redwood City, CA 94063, USA"}

@String{pub-NIST                = "National Institute for Standards
                                  and Technology"}

@String{pub-NIST:adr            = "Gaithersburg, MD, USA"}

@String{pub-NEW-RIDERS          = "New Riders Publishing"}

@String{pub-NEW-RIDERS:adr      = "Carmel, IN, USA"}

@String{pub-ORA                 = "O'Reilly \& {Associates, Inc.}"}

@String{pub-ORA:adr             = "103a Morris Street, Sebastopol, CA
                                  95472, USA, Tel: +1 707 829 0515,
                                  and 90 Sherman Street, Cambridge, MA
                                  02140, USA, Tel: +1 617 354 5800"}

@String{pub-ORA-MEDIA           = "O'Reilly Media, Inc."}

@String{pub-ORA-MEDIA:adr       = "1005 Gravenstein Highway North, Sebastopol,
                                  CA 95472, USA"}

@String{pub-OSBORNE             = "Osborne/McGraw-Hill"}

@String{pub-OSBORNE:adr         = "Berkeley, CA, USA"}

@String{pub-PEACHPIT            = "Peachpit Press, Inc."}

@String{pub-PEACHPIT:adr        = "1085 Keith Avenue, Berkeley, CA 94708, USA"}

@String{pub-PH                  = "Pren{\-}tice-Hall"}

@String{pub-PH:adr              = "Englewood Cliffs, NJ 07632, USA"}

@String{pub-PHPTR               = "Pren{\-}tice-Hall PTR"}

@String{pub-PHPTR:adr           = "Upper Saddle River, NJ 07458, USA"}

@String{pub-PRIMA               = "Prima Publishing"}

@String{pub-PRIMA:adr           = "Roseville, CA, USA"}

@String{pub-QUE                 = "Que Corporation"}

@String{pub-QUE:adr             = "Indianapolis, IN, USA"}

@String{pub-SAMS                = "SAMS Publishing"}

@String{pub-SAMS:adr            = "Indianapolis, IN, USA"}

@String{pub-SV                  = "Springer-Verlag Inc."}

@String{pub-SV:adr              = "New York, NY, USA"}

@String{pub-SYBEX               = "Sybex"}

@String{pub-SYBEX:adr           = "2021 Challenger Driver, Suite 100,
                                  Alameda, CA 94501, USA"}

@String{pub-WILEY               = "Wiley"}

@String{pub-WILEY:adr           = "New York, NY, USA"}

@String{pub-WROX                = "Wrox Press"}

@String{pub-WROX:adr            = "Chicago, IL, USA"}

%%% ====================================================================
%%% Series abbreviations:
@String{ser-LNCS                = "Lecture Notes in Computer Science"}

%%% ====================================================================
%%% Bibliography entries.
  author =       "Sven Apel and Delesley Hutchins",
  title =        "A calculus for uniform feature composition",
  journal =      j-TOPLAS,
  volume =       "32",
  number =       "5",
  pages =        "19:1--19:??",
  month =        may,
  year =         "2010",
  CODEN =        "ATPSDT",
  DOI =          "",
  ISSN =         "0164-0925 (print), 1558-4593 (electronic)",
  ISSN-L =       "0164-0925",
  bibdate =      "Fri May 21 12:28:30 MDT 2010",
  bibsource =    ";
  abstract =     "The goal of {\em feature-oriented programming\/} (FOP)
                 is to modularize software systems in terms of features.
                 A {\em feature\/} refines the content of a base
                 program. Both base programs and features may contain
                 various kinds of software artifacts, for example,
                 source code in different languages, models, build
                 scripts, and documentation. We and others have noticed
                 that when composing features, different kinds of
                 software artifacts can be refined in a uniform way,
                 regardless of what they represent. We present gDeep, a
                 core calculus for feature composition, which captures
                 the language independence of FOP; it can be used to
                 compose features containing many different kinds of
                 artifact in a type-safe way. The calculus allows us to
                 gain insight into the principles of FOP and to define
                 general algorithms for feature composition and
                 validation. We provide the formal syntax, operational
                 semantics, and type system of gDeep and outline how
                 languages like Java, Haskell, Bali, and XML can be
                 plugged in.",
  acknowledgement = ack-nhfb,
  articleno =    "19",
  fjournal =     "ACM Transactions on Programming Languages and
  journal-URL =  "",
  keywords =     "feature composition; Feature-oriented programming;
                 principle of uniformity; type systems",

  author =       "Geert Jan Bex and Frank Neven and Thomas Schwentick
                 and Stijn Vansummeren",
  title =        "Inference of concise regular expressions and {DTDs}",
  journal =      j-TODS,
  volume =       "35",
  number =       "2",
  pages =        "11:1--11:??",
  month =        apr,
  year =         "2010",
  CODEN =        "ATDSD3",
  DOI =          "",
  ISSN =         "0362-5915 (print), 1557-4644 (electronic)",
  ISSN-L =       "0362-5915",
  bibdate =      "Wed Apr 28 13:44:08 MDT 2010",
  bibsource =    ";
  abstract =     "We consider the problem of inferring a concise
                 Document Type Definition (DTD) for a given set of
                 XML-documents, a problem that basically reduces to
                 learning {\em concise\/} regular expressions from
                 positive examples strings. We identify two classes of
                 concise regular expressions --- the single occurrence
                 regular expressions (SOREs) and the chain regular
                 expressions (CHAREs) --- that capture the far majority
                 of expressions used in practical DTDs. For the
                 inference of SOREs we present several algorithms that
                 first infer an automaton for a given set of example
                 strings and then translate that automaton to a
                 corresponding SORE, possibly repairing the automaton
                 when no equivalent SORE can be found. In the process,
                 we introduce a novel automaton to regular expression
                 rewrite technique which is of independent interest.
                 When only a very small amount of XML data is available,
                 however (for instance when the data is generated by Web
                 service requests or by answers to queries), these
                 algorithms produce regular expressions that are too
                 specific. Therefore, we introduce a novel learning
                 algorithm crx that directly infers CHAREs (which form a
                 subclass of SOREs) without going through an automaton
                 representation. We show that crx performs very well
                 within its target class on very small datasets.",
  acknowledgement = ack-nhfb,
  articleno =    "11",
  fjournal =     "ACM Transactions on Database Systems",
  journal-URL =  "",
  keywords =     "Regular expressions; schema inference; XML",

  author =       "Angela Bonifati and Elaine Chang and Terence Ho and
                 Laks V. Lakshmanan and Rachel Pottinger and Yongik
  title =        "Schema mapping and query translation in heterogeneous
                 {P2P XML} databases",
  journal =      j-VLDB-J,
  volume =       "19",
  number =       "2",
  pages =        "231--256",
  month =        apr,
  year =         "2010",
  CODEN =        "VLDBFR",
  DOI =          "",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Wed Apr 21 16:41:50 MDT 2010",
  bibsource =    ";
  abstract =     "Peers in a peer-to-peer data management system often
                 have heterogeneous schemas and no mediated global
                 schema. To translate queries across peers, we assume
                 each peer provides correspondences between its schema
                 and a small number of other peer schemas. We focus on
                 query reformulation in the presence of heterogeneous
                 XML schemas, including data---metadata conflicts. We
                 develop an algorithm for inferring precise mapping
                 rules from informal schema correspondences. We define
                 the semantics of query answering in this setting and
                 develop query translation algorithm. Our translation
                 handles an expressive fragment of XQuery and works both
                 along and against the direction of mapping rules. We
                 describe the HePToX heterogeneous P2P XML data
                 management system which incorporates our results. We
                 report the results of extensive experiments on HePToX
                 on both synthetic and real datasets. We demonstrate our
                 system utility and scalability on different P2P
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "",
  keywords =     "Heterogeneous Peer-to-Peer XML databases; Schema
                 mapping; XML query translation",

  author =       "Ramadhana Bramandia and Jiefeng Cheng and Byron Choi
                 and Jeffrey Xu Yu",
  title =        "Optimizing updates of recursive {XML} views of
  journal =      j-VLDB-J,
  volume =       "18",
  number =       "6",
  pages =        "1313--1333",
  month =        dec,
  year =         "2010",
  CODEN =        "VLDBFR",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Tue Mar 16 08:21:44 MDT 2010",
  bibsource =    ";
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "",

  author =       "Gregory Buehrer and Srinivasan Parthasarathy and
                 Shirish Tatikonda",
  title =        "A distributed placement service for graph-structured
                 and tree-structured data",
  journal =      j-SIGPLAN,
  volume =       "45",
  number =       "5",
  pages =        "355--356",
  month =        may,
  year =         "2010",
  CODEN =        "SINODQ",
  DOI =          "",
  ISSN =         "0362-1340 (print), 1523-2867 (print), 1558-1160
  ISSN-L =       "0362-1340",
  bibdate =      "Tue Aug 31 22:39:18 MDT 2010",
  bibsource =    ";
  abstract =     "Effective data placement strategies can enhance the
                 performance of data-intensive applications implemented
                 on high end computing clusters. Such strategies can
                 have a significant impact in localizing the
                 computation, in minimizing synchronization
                 (communication) costs, in enhancing reliability (via
                 strategic replication policies), and in ensuring a
                 balanced workload or enhancing the available bandwidth
                 from massive storage devices (e.g. disk

                 Existing work has largely targeted the placement of
                 relatively simple data types or entities (e.g.
                 elements, vectors, sets, and arrays). Here we
                 investigate several hash-based distributed data
                 placement methods targeting tree- and graph- structured
                 data, and develop a locality enhancing placement
                 service for large cluster systems. Target applications
                 include the placement of a single large graph (e.g. Web
                 graph), a single large tree (e.g. large XML file), a
                 forest of graphs or trees (e.g. XML database) and other
                 specialized graph data types - bi-partite (query-click
                 graphs), directed acyclic graphs etc. We empirically
                 evaluate our service by demonstrating its use in
                 improving mining executions for pattern discovery,
                 nearest neighbor searching, graph computations, and
                 applications that combine link and content analysis.",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM SIGPLAN Notices",
  journal-URL =  "",
  keywords =     "data placement; distributed computing; structured

  author =       "Shih-Chien Chou and Chun-Hao Huang",
  title =        "An extended {XACML} model to ensure secure information
                 access for {Web} services",
  journal =      j-J-SYST-SOFTW,
  volume =       "83",
  number =       "1",
  pages =        "77--84",
  month =        jan,
  year =         "2010",
  CODEN =        "JSSODM",
  ISSN =         "0164-1212",
  ISSN-L =       "0164-1212",
  bibdate =      "Tue Sep 7 07:27:05 MDT 2010",
  bibsource =    ";
  acknowledgement = ack-nhfb,
  fjournal =     "The Journal of systems and software",
  journal-URL =  "",

  author =       "Edith Cohen and Haim Kaplan and Tova Milo",
  title =        "Labeling Dynamic {XML} Trees",
  journal =      j-SIAM-J-COMPUT,
  volume =       "39",
  number =       "5",
  pages =        "2048--2074",
  month =        "????",
  year =         "2010",
  CODEN =        "SMJCAT",
  DOI =          "",
  ISSN =         "0097-5397 (print), 1095-7111 (electronic)",
  ISSN-L =       "0097-5397",
  bibdate =      "Tue May 18 08:22:16 MDT 2010",
  bibsource =    ";
  acknowledgement = ack-nhfb,
  fjournal =     "SIAM Journal on Computing",
  journal-URL =  "",

  author =       "Mariano P. Consens and Ren{\'e}e J. Miller and Flavio
                 Rizzolo and Alejandro A. Vaisman",
  title =        "Exploring {XML} {Web} collections with {DescribeX}",
  journal =      j-TWEB,
  volume =       "4",
  number =       "3",
  pages =        "11:1--11:??",
  month =        jul,
  year =         "2010",
  CODEN =        "????",
  DOI =          "",
  ISSN =         "1559-1131 (print), 1559-114X (electronic)",
  ISSN-L =       "1559-1131",
  bibdate =      "Sat Aug 14 15:42:40 MDT 2010",
  bibsource =    ";
  abstract =     "As Web applications mature and evolve, the nature of
                 the semistructured data that drives these applications
                 also changes. An important trend is the need for
                 increased flexibility in the structure of Web
                 documents. Hence, applications cannot rely solely on
                 schemas to provide the complex knowledge needed to
                 visualize, use, query and manage documents. Even when
                 XML Web documents are valid with regard to a schema,
                 the actual structure of such documents may exhibit
                 significant variations across collections for several
                 reasons: the schema may be very lax (e.g., RSS feeds),
                 the schema may be large and different subsets of it may
                 be used in different documents (e.g., industry
                 standards like UBL), or open content models may allow
                 arbitrary schemas to be mixed (e.g., RSS extensions
                 like those used for podcasting). For these reasons,
                 many applications that incorporate XPath queries to
                 process a large Web document collection require an
                 understanding of the actual structure present in the
                 collection, and not just the schema.\par

                 To support modern Web applications, we introduce
                 DescribeX, a powerful framework that is capable of
                 describing complex XML summaries of Web collections.
                 DescribeX supports the construction of heterogeneous
                 summaries that can be declaratively defined and refined
                 by means of axis path regular expression (AxPREs).
                 AxPREs provide the flexibility necessary for
                 declaratively defining complex mappings between
                 instance nodes (in the documents) and summary nodes.
                 These mappings are capable of expressing order and
                 cardinality, among other properties, which can
                 significantly help in the understanding of the
                 structure of large collections of XML documents and
                 enhance the performance of Web applications over these
                 collections. DescribeX captures most summary proposals
                 in the literature by providing (for the first time) a
                 common declarative definition for them. Experimental
                 results demonstrate the scalability of DescribeX
                 summary operations (summary creation, as well as
                 refinement and stabilization, two key enablers for
                 tailoring summaries) on multi-gigabyte Web
  acknowledgement = ack-nhfb,
  articleno =    "11",
  fjournal =     "ACM Transactions on the Web (TWEB)",
  keywords =     "Semistructured data; structural summaries; XML;

  author =       "Jason Jianxun Ding and Abdul Waheed and Jingnan Yao
                 and Laxmi N. Bhuyan",
  title =        "Performance characterization of multi-thread and
                 multi-core processors based {XML} application oriented
                 networking systems",
  journal =      j-J-PAR-DIST-COMP,
  volume =       "70",
  number =       "5",
  pages =        "584--597",
  month =        may,
  year =         "2010",
  CODEN =        "JPDCER",
  ISSN =         "0743-7315 (print), 1096-0848 (electronic)",
  ISSN-L =       "0743-7315",
  bibdate =      "Wed Sep 1 16:27:28 MDT 2010",
  bibsource =    ";
  acknowledgement = ack-nhfb,
  fjournal =     "Journal of Parallel and Distributed Computing",
  journal-URL =  "",

  author =       "Kathleen Fisher and Yitzhak Mandelbaum and David
  title =        "The next 700 data description languages",
  journal =      j-J-ACM,
  volume =       "57",
  number =       "2",
  pages =        "10:1--10:??",
  month =        jan,
  year =         "2010",
  CODEN =        "JACOAH",
  DOI =          "",
  ISSN =         "0004-5411",
  ISSN-L =       "0004-5411",
  bibdate =      "Mon Mar 15 11:20:36 MDT 2010",
  bibsource =    ";
  abstract =     "In the spirit of Landin, we present a calculus of
                 dependent types to serve as the semantic foundation for
                 a family of languages called {\em data description
                 languages}. Such languages, which include pads,
                 datascript, and packettypes, are designed to facilitate
                 programming with {\em ad hoc data}, that is, data not
                 in well-behaved relational or xml formats. In the
                 calculus, each type describes the physical layout and
                 semantic properties of a data source. In the semantics,
                 we interpret types simultaneously as the in-memory
                 representation of the data described and as parsers for
                 the data source. The parsing functions are robust,
                 automatically detecting and recording errors in the
                 data stream without halting parsing. We show the
                 parsers are type-correct, returning data whose type
                 matches the simple-type interpretation of the
                 specification. We also prove the parsers are
                 ``error-correct,'' accurately reporting the number of
                 physical and semantic errors that occur in the returned
                 data. We use the calculus to describe the features of
                 various data description languages, and we discuss how
                 we have used the calculus to improve pads.",
  acknowledgement = ack-nhfb,
  articleno =    "10",
  fjournal =     "Journal of the ACM",
  journal-URL =  "",
  keywords =     "ad hoc data formats; context-sensitive grammars; data
                 description languages; data processing; data-dependent
                 grammars; dependent types; domain-specific languages;
                 PADS; Parsing",

  author =       "Jun Gao and Jiaheng Lu and Tengjiao Wang and Dongqing
  title =        "Efficient evaluation of query rewriting plan over
                 materialized {XML} view",
  journal =      j-J-SYST-SOFTW,
  volume =       "83",
  number =       "6",
  pages =        "1029--1038",
  month =        jun,
  year =         "2010",
  CODEN =        "JSSODM",
  ISSN =         "0164-1212",
  ISSN-L =       "0164-1212",
  bibdate =      "Tue Sep 7 07:27:05 MDT 2010",
  bibsource =    ";
  acknowledgement = ack-nhfb,
  fjournal =     "The Journal of systems and software",
  journal-URL =  "",

  author =       "Jeong Hee Hwang and Keun Ho Ryu",
  title =        "A weighted common structure based clustering technique
                 for {XML} documents",
  journal =      j-J-SYST-SOFTW,
  volume =       "83",
  number =       "7",
  pages =        "1267--1274",
  month =        jul,
  year =         "2010",
  CODEN =        "JSSODM",
  ISSN =         "0164-1212",
  ISSN-L =       "0164-1212",
  bibdate =      "Tue Sep 7 07:27:06 MDT 2010",
  bibsource =    ";
  acknowledgement = ack-nhfb,
  fjournal =     "The Journal of systems and software",
  journal-URL =  "",

  author =       "Yildiray Kabak and Asuman Dogac",
  title =        "A survey and analysis of electronic business document
  journal =      j-COMP-SURV,
  volume =       "42",
  number =       "3",
  pages =        "11:1--11:??",
  month =        mar,
  year =         "2010",
  CODEN =        "CMSVAN",
  DOI =          "",
  ISSN =         "0360-0300 (print), 1557-7341 (electronic)",
  ISSN-L =       "0360-0300",
  bibdate =      "Thu Mar 25 09:34:56 MDT 2010",
  bibsource =    ";
  abstract =     "No document standard is sufficient for all purposes
                 because the requirements significantly differ among
                 businesses, industries, and geopolitical regions. On
                 the other hand, the ultimate aim of business document
                 interoperability is to exchange business data among
                 partners without any prior agreements related to the
                 document syntax and semantics. Therefore, an important
                 characteristic of a document standard is its ability to
                 adapt to different contexts, its extensibility, and its
                 customization. The UN/CEFACT Core Component Technical
                 Specification (CCTS) is an important landmark in this

                 In this article, we present a survey and an analysis of
                 some of the prominent UN/CEFACT CCTS-based electronic
                 document standards. We describe their document design
                 principles and discuss how they handle customization
                 and extensibility. We address their industry relevance
                 and the recent efforts for their harmonization and
                 convergence. We conclude by mentioning some emerging
                 efforts for the semantic interoperability of different
                 document standards.",
  acknowledgement = ack-nhfb,
  articleno =    "11",
  fjournal =     "ACM Computing Surveys",
  journal-URL =  "",
  keywords =     "Document Interoperability Standards; eBusiness; Global
                 Standards One (GS1) XML; OAGIS Business Object
                 Documents (BODs); OASIS Universal Business Language
                 (UBL); UN/CEFACT Core Component Technical Specification

  author =       "Ki-Hoon Lee and Kyu-Young Whang and Wook-Shin Han and
                 Min-Soo Kim",
  title =        "Structural consistency: enabling {XML} keyword search
                 to eliminate spurious results consistently",
  journal =      j-VLDB-J,
  volume =       "19",
  number =       "4",
  pages =        "503--529",
  month =        aug,
  year =         "2010",
  CODEN =        "VLDBFR",
  DOI =          "",
  ISSN =         "1066-8888 (print), 0949-877X (electronic)",
  ISSN-L =       "1066-8888",
  bibdate =      "Wed Aug 18 12:06:22 MDT 2010",
  bibsource =    ";
  abstract =     "XML keyword search is a user-friendly way to query XML
                 data using only keywords. In XML keyword search, to
                 achieve high precision without sacrificing recall, it
                 is important to remove spurious results not intended by
                 the user. Efforts to eliminate spurious results have
                 enjoyed some success using the concepts of LCA or its
                 variants, SLCA and MLCA. However, existing methods
                 still could find many spurious results. The fundamental
                 cause for the occurrence of spurious results is that
                 the existing methods try to eliminate spurious results
                 locally without global examination of all the query
                 results and, accordingly, some spurious results are not
                 consistently eliminated. In this paper, we propose a
                 novel keyword search method that removes spurious
                 results consistently by exploiting the new concept of
                 structural consistency. We define structural
                 consistency as a property that is preserved if there is
                 no query result having an ancestor-descendant
                 relationship at the schema level with any other query
                 results. A naive solution to obtain structural
                 consistency would be to compute all the LCAs (or
                 variants) and then to remove spurious results according
                 to structural consistency. Obviously, this approach
                 would always be slower than existing LCA-based ones. To
                 speed up structural consistency checking, we must be
                 able to examine the query results at the schema level
                 without generating all the LCAs. However, this is a
                 challenging problem since the schema-level query
                 results do not homomorphically map to the
                 instance-level query results, causing serious false
                 dismissal. We present a comprehensive and practical
                 solution to this problem and formally prove that this
                 solution preserves structural consistency at the schema
                 level without incurring false dismissal. We also
                 propose a relevance-feedback-based solution for the
                 problem where our method has low recall, which occurs
                 when it is not the user's intention to find more
                 specific results. This solution has been prototyped in
                 a full-fledged object-relational DBMS Odysseus
                 developed at KAIST. Experimental results using real and
                 synthetic data sets show that, compared with the
                 state-of-the-art methods, our solution significantly
                 (1) improves precision while providing comparable
                 recall for most queries and (2) enhances the query
                 performance by removing spurious results early.",
  acknowledgement = ack-nhfb,
  fjournal =     "VLDB Journal: Very Large Data Bases",
  journal-URL =  "",
  keywords =     "Keyword search; Odysseus DBMS; Spurious results;
                 Structural consistency; Structural summary; XML",

  author =       "Xudong Lin and Ning Wang and De Xu and Xiaoning Zeng",
  title =        "A novel {XML} keyword query approach using entity
  journal =      j-J-SYST-SOFTW,
  volume =       "83",
  number =       "6",
  pages =        "990--1003",
  month =        jun,
  year =         "2010",
  CODEN =        "JSSODM",
  ISSN =         "0164-1212",
  ISSN-L =       "0164-1212",
  bibdate =      "Tue Sep 7 07:27:05 MDT 2010",
  bibsource =    ";
  acknowledgement = ack-nhfb,
  fjournal =     "The Journal of systems and software",
  journal-URL =  "",

  author =       "Ziyang Liu and Yu Huang and Yi Chen",
  title =        "Improving {XML} search by generating and utilizing
                 informative result snippets",
  journal =      j-TODS,
  volume =       "35",
  number =       "3",
  pages =        "19:1--19:??",
  month =        jul,
  year =         "2010",
  CODEN =        "ATDSD3",
  DOI =          "",
  ISSN =         "0362-5915 (print), 1557-4644 (electronic)",
  ISSN-L =       "0362-5915",
  bibdate =      "Wed Jul 28 15:53:01 MDT 2010",
  bibsource =    ";
  abstract =     "Snippets are used by almost every text search engine
                 to complement the ranking scheme in order to
                 effectively handle user searches, which are inherently
                 ambiguous and whose relevance semantics are difficult
                 to assess. Despite the fact that XML is a standard
                 representation format of Web data, research on
                 generating result snippets for XML search remains

                 To tackle this important yet open problem, in this
                 article, we present a system extract which generates
                 snippets for XML search results. We identify that a
                 good XML result snippet should be a meaningful
                 information unit of a small size that effectively
                 summarizes this query result and differentiates it from
                 others, according to which users can quickly assess the
                 relevance of the query result. We have designed and
                 implemented a novel algorithm to satisfy these
                 requirements. Furthermore, we propose to cluster the
                 query results based on their snippets. Since XML result
                 clustering can only be done at query time,
                 snippet-based clustering significantly improves the
                 efficiency while compromising little clustering
                 accuracy. We verified the efficiency and effectiveness
                 of our approach through experiments.",
  acknowledgement = ack-nhfb,
  articleno =    "19",
  fjournal =     "ACM Transactions on Database Systems",
  journal-URL =  "",
  keywords =     "clustering; keyword search; snippets; XML",

  author =       "Ziyang Liu and Yi Chen",
  title =        "Return specification inference and result clustering
                 for keyword search on {XML}",
  journal =      j-TODS,
  volume =       "35",
  number =       "2",
  pages =        "10:1--10:??",
  month =        apr,
  year =         "2010",
  CODEN =        "ATDSD3",
  DOI =          "",
  ISSN =         "0362-5915 (print), 1557-4644 (electronic)",
  ISSN-L =       "0362-5915",
  bibdate =      "Wed Apr 28 13:44:08 MDT 2010",
  bibsource =    ";
  abstract =     "Keyword search enables Web users to easily access XML
                 data without the need to learn a structured query
                 language and to study possibly complex data schemas.
                 Existing work has addressed the problem of selecting
                 qualified data nodes that match keywords and connecting
                 them in a meaningful way, in the spirit of inferring
                 the {\em where clause\/} in XQuery. However, how to
                 infer the {\em return clause\/} for keyword searches is
                 an open problem.\par

                 To address this challenge, we present a keyword search
                 engine for data-centric XML, XSeek, to infer the
                 semantics of the search and identify return nodes
                 effectively. XSeek recognizes possible entities and
                 attributes inherently represented in the data. It also
                 distinguishes between predicates and return
                 specifications in query keywords. Then based on the
                 analysis of both XML data structures and keyword
                 patterns, XSeek generates return nodes. Furthermore,
                 when the query is ambiguous and it is hard or
                 impossible to determine the desirable return
                 information, XSeek clusters the query results according
                 to their semantics based on the user-specified
                 granularity, and enables the user to easily browse and
                 select the desired ones. Extensive experimental studies
                 show the effectiveness and efficiency of XSeek.",
  acknowledgement = ack-nhfb,
  articleno =    "10",
  fjournal =     "ACM Transactions on Database Systems",
  journal-URL =  "",
  keywords =     "keyword search; result clustering; XML",

  author =       "Wim Martens and Frank Neven and Thomas Schwentick",
  title =        "Complexity of Decision Problems for {XML} Schemas and
                 Chain Regular Expressions",
  journal =      j-SIAM-J-COMPUT,
  volume =       "39",
  number =       "4",
  pages =        "1486--1530",
  month =        "????",
  year =         "2010",
  CODEN =        "SMJCAT",
  DOI =          "",
  ISSN =         "0097-5397 (print), 1095-7111 (electronic)",
  ISSN-L =       "0097-5397",
  bibdate =      "Tue May 18 08:22:14 MDT 2010",
  bibsource =    ";
  acknowledgement = ack-nhfb,
  fjournal =     "SIAM Journal on Computing",
  journal-URL =  "",

  author =       "Vittorio Miori and Dario Russo and Massimo Aliberti",
  title =        "Domotic technologies incompatibility becomes user
  journal =      j-CACM,
  volume =       "53",
  number =       "1",
  pages =        "153--157",
  month =        jan,
  year =         "2010",
  CODEN =        "CACMA2",
  DOI =          "",
  ISSN =         "0001-0782 (print), 1557-7317 (electronic)",
  ISSN-L =       "0001-0782",
  bibdate =      "Thu Feb 4 17:12:32 MST 2010",
  bibsource =    ";
  abstract =     "The potential of current technologies in smart
                 automation has been largely unexploited. Pervasive
                 computing vision is still far from being achieved,
                 especially with regard to Domotics and home
                 applications. In fact, even though many implementations
                 have started to appear in several contexts, few
                 applications have been made available for the home
                 environment and the general public. This is mainly due
                 to the segmentation of standards and proprietary
                 solutions, which are currently confusing the market
                 with a sparse offer of uninteroperable devices and

                 Although modern houses are equipped with smart
                 technological appliances, still very few of these
                 appliances can be seamlessly connected to each

                 Moreover, inter-working capabilities are required
                 beyond house boundaries, towards external services and
                 towards other houses as nodes of a global

                 Therefore, the main goal of this research is to find
                 solutions to the problem of interoperability that will
                 be in line with open and widely recognized

                 The result is a computing framework based on open
                 communication standards, capable of abstracting the
                 peculiarities of underlying heterogeneous technologies,
                 and letting them co-exist and interwork, without
                 eliminating their differences. Interoperability can
                 thus be made potentially feasible between any domotic
                 technology, both currently existing, and still to be

                 Currently, domotic technology vendors concentrate on
                 building closed relationships with their customers, and
                 leveraging their economic investments by establishing
                 barriers against new manufacturers entering the

                 Examples of current domotic protocols are X10, Konnex,
                 LonWorks, UPnP, HAVi, and Jini supporting various
                 communication standards (Ethernet, FireWire, Bluetooth,
                 ZigBee, IrDA and proprietary buses). We believe that no
                 domotic technology currently has the potential to
                 actually play a leading role. Within this wide and
                 heterogeneous framework, the market logic is to tie
                 consumers to a particular domotic protocol, which then
                 forces them to only purchase conforming devices in
                 order to keep a consistent level of

                 In recent years several interesting and innovative
                 solutions have emerged, with a reasonable level of
                 scalability and dependability, providing
                 interoperability among heterogeneous home

                 Twente University has proposed a solution that aims at
                 supporting heterogeneous technologies (including legacy
                 ones) with a 'cluster cultures' approach. The
                 architecture outlines a 'touch and play' system which,
                 at device registration time, enables a
                 zero-configuration environment for the exchange of
                 credentials among its gateways and to register device
                 services in a hierarchical structure. The architecture
                 provides a high level of security by using
                 cryptographic algorithms.\par

                 Waseda University have proposed a framework designed to
                 easily enable the integration of legacy middleware and
                 legacy services and clients, with a predefined path for
                 the inclusion of new, future, middleware. This is
                 accomplished mainly through the use of a Virtual
                 Service Gateway. This connects one piece of middleware
                 to another by exploiting a Protocol Conversion Manager,
                 whose task is to convert the different middleware
                 protocols into the specific internal protocol used by
                 the Virtual Service Gateway. Information about the
                 location and functions of services is provided by a
                 Virtual Service Repository.\par

                 Another interesting project is the 'Domotic House
                 Gateway.' It implements an event-based mechanism which
                 is used to exchange messages between the single device
                 and the system. These events are internally converted
                 into logical events so as to clearly separate the
                 actual physical issues from the semantics that goes
                 beyond the devices and their role within the house. One
                 level of the architecture implements a rule-based core
                 that can be dynamically adapted either by the system
                 itself or manually through external interfaces. Each
                 device needs a device driver, which is responsible for
                 translating its low level or hardware states and
                 activities into events that can be managed by the

                 Another promising approach, in line with our research,
                 is proposed by the Open Building Information Exchange
                 group who are working to create standard XML and Web
                 Services guidelines to facilitate information exchange
                 among mechanical and electrical systems in building

                 One such important European project in this context is
                 Amigo. This project was aimed at Ambient Intelligence
                 features for the networked home environment and the
                 usability of the system was among its main goals and
                 included three major guidelines: user-friendly
                 interfaces, interoperability, and automatic discovery
                 of devices and services.\par

                 All these projects resolved the interoperability
                 problem with several approaches, all of which are
                 different from what we consider, in our vision, as the
                 optimal solutions.\par

                 Lastly, we enlist a prototype previously created by our
                 research laboratory. This solution had the limitation
                 of abstracting each device typology with a Web service
                 implementing their specific functionalities. The
                 implementation of a new ad hoc Web service was needed
                 whenever a new category of device needed to be included
                 in the network. In addition, this prototype solved the
                 problem of cooperation by virtualizing devices
                 belonging to each domotic system onto the others. This
                 solution, however, had a drawback: the same device
                 appeared virtually replicated on every single domotic
                 system, thus creating data replications and possible
                 consistency problems.",
  acknowledgement = ack-nhfb,
  fjournal =     "Communications of the ACM",
  journal-URL =  "",

  author =       "Mark Pilgrim",
  title =        "{HTML5}: up and running",
  publisher =    pub-ORA,
  address =      pub-ORA:adr,
  pages =        "250",
  year =         "2010",
  ISBN =         "0-596-80602-7",
  ISBN-13 =      "978-0-596-80602-6",
  LCCN =         "????",
  bibdate =      "Wed Jul 28 20:15:48 MDT 2010",
  bibsource =    ";
  acknowledgement = ack-nhfb,

  author =       "Andrea Romei and Franco Turini",
  title =        "{XML} data mining",
  journal =      j-SPE,
  volume =       "40",
  number =       "2",
  pages =        "101--130",
  day =          "??",
  month =        feb,
  year =         "2010",
  CODEN =        "SPEXBL",
  DOI =          "",
  ISSN =         "0038-0644 (print), 1097-024X (electronic)",
  ISSN-L =       "0038-0644",
  bibdate =      "Wed Mar 17 10:16:22 MDT 2010",
  bibsource =    ";
  acknowledgement = ack-nhfb,
  fjournal =     "Software---Practice and Experience",
  journal-URL =  "",
  onlinedate =   "Dec 23 2009 8:58AM",

  author =       "Christopher Schmitt",
  title =        "{CSS} cookbook",
  publisher =    pub-ORA,
  address =      pub-ORA:adr,
  edition =      "Third",
  pages =        "xxiv + 702",
  year =         "2010",
  ISBN =         "0-596-15593-X (paperback)",
  ISBN-13 =      "978-0-596-15593-3 (paperback)",
  LCCN =         "TK5105.888 .S3524 2010",
  bibdate =      "Wed Jul 28 09:08:49 MDT 2010",
  bibsource =    ";
  note =         "Foreword by Dan Cederholm.",
  acknowledgement = ack-nhfb,
  remark =       "Updated for Firefox 3, IE 8, and Chrome.",
  subject =      "Cascading style sheets; Web sites; Design; Cascading
                 Style Sheets 2.1; Cascading Style Sheets",

  author =       "P. Silvasti and S. Sippu and E. Soisalon-Soininen",
  title =        "Evaluating Linear {XPath} Expressions by
                 Pattern-Matching Automata",
  journal =      j-J-UCS,
  volume =       "16",
  number =       "5",
  pages =        "833--??",
  month =        "????",
  year =         "2010",
  CODEN =        "????",
  ISSN =         "0948-6968",
  ISSN-L =       "0948-6968",
  bibdate =      "Wed Aug 25 21:53:00 MDT 2010",
  bibsource =    ";
  URL =          "",
  acknowledgement = ack-nhfb,
  fjournal =     "J.UCS: Journal of Universal Computer Science",
  journal-URL =  "",

  author =       "Heinrich Stamerjohanns and Michael Kohlhase and Deyan
                 Ginev and Catalin David and Bruce Miller",
  title =        "Transforming Large Collections of Scientific
                 Publications to {XML}",
  journal =      j-MATH-COMPUT-SCI,
  volume =       "3",
  number =       "3",
  pages =        "299--307",
  month =        may,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "1661-8270 (print), 1661-8289 (electronic)",
  ISSN-L =       "1661-8270",
  bibdate =      "Sun Aug 22 09:02:18 MDT 2010",
  bibsource =    ";
  URL =          "",
  abstract =     "We describe an experiment transforming large
                 collections of {\LaTeX} documents to more
                 machine-understandable representations. Concretely, we
                 are translating the collection of scientific
                 publications of the Cornell e-Print Archive ({ar$ \chi
                 $}iv) using {\LaTeX{}ML}, a {\LaTeX} to XML converter
                 currently under development. While the long-term goal
                 is a large body of scientific documents available for
                 semantic analysis, search indexing and other
                 experimentation, the immediate goals are tools for
                 creating such corpora. The first task of our arXMLiv
                 project is to develop {\LaTeX{}ML} bindings for the
                 (thousands of) {\LaTeX} classes and packages used in
                 the {ar$ \chi $}iv collection, as well as methods for
                 coping with the eccentricities that {\TeX} encourages.
                 We have created a distributed build system that runs
                 {\LaTeX{}ML} over the collection, in part or entirely,
                 while collecting statistics about missing bindings and
                 other errors. This guides debugging and development
                 efforts, leading to iterative improvements in both the
                 tools and the quality of the converted corpus. The
                 build system thus serves as both a production
                 conversion engine and software test harness. We have
                 now processed the complete {ar$ \chi $}iv collection
                 through 2006 consisting of more than 400,000 documents
                 (a complete run is a processor-year-size undertaking),
                 continuously improving our success rate. We are now
                 able to convert more than 90\% of these documents to
                 XHTML $+$ MathML. We consider over 60\% to be
                 successes, converted with no or minor warnings. While
                 the remaining 30\% can also be converted, their quality
                 is doubtful, due to unsupported macros or conversion
  acknowledgement = ack-nhfb,
  fjournal =     "Mathematics in Computer Science",
  journal-URL =  "",

  author =       "Jonathan Stark",
  title =        "Building {iPhone} apps with {HTML}, {CSS}, and
                 {JavaScript}: Making {App Store} apps without
                 {Objective-C} or {Cocoa}",
  publisher =    pub-ORA-MEDIA,
  address =      pub-ORA-MEDIA:adr,
  pages =        "xv + 166",
  year =         "2010",
  ISBN =         "1-4493-8023-9, 0-596-80578-0",
  ISBN-13 =      "978-1-4493-8023-6, 978-0-596-80578-4",
  LCCN =         "????",
  bibdate =      "Wed Jul 28 09:12:55 MDT 2010",
  bibsource =    ";
  acknowledgement = ack-nhfb,
  subject =      "Cascading Style Sheets; HTML (document markup
                 language); computer software; development; iPhone
                 (Smartphone); programming; JavaScript (computer program

  author =       "Andrea Tagarelli and Sergio Greco",
  title =        "Semantic clustering of {XML} documents",
  journal =      j-TOIS,
  volume =       "28",
  number =       "1",
  pages =        "3:1--3:??",
  month =        jan,
  year =         "2010",
  CODEN =        "ATISET",
  ISSN =         "1046-8188",
  ISSN-L =       "0734-2047",
  bibdate =      "Mon Mar 15 12:37:04 MDT 2010",
  bibsource =    ";
  acknowledgement = ack-nhfb,
  articleno =    "3",
  fjournal =     "ACM Transactions on Information Systems",

  author =       "Balder {Ten Cate} and Luc Segoufin",
  title =        "Transitive closure logic, and nested tree walking
                 automata, and {Xpath}",
  journal =      j-J-ACM,
  volume =       "57",
  number =       "3",
  pages =        "18:1--18:??",
  month =        mar,
  year =         "2010",
  CODEN =        "JACOAH",
  DOI =          "",
  ISSN =         "0004-5411",
  ISSN-L =       "0004-5411",
  bibdate =      "Thu Mar 25 09:08:48 MDT 2010",
  bibsource =    ";
  abstract =     "We study FO(MTC), first-order logic with monadic
                 transitive closure, a logical formalism in between FO
                 and MSO on trees. We characterize the expressive power
                 of FO(MTC) in terms of nested tree-walking automata.
                 Using the latter, we show that FO(MTC) is strictly less
                 expressive than MSO, solving an open problem. We also
                 present a temporal logic on trees that is expressively
                 complete for FO(MTC), in the form of an extension of
                 the XML document navigation language XPath with two
                 operators: the Kleene star for taking the transitive
                 closure of path expressions, and a subtree
                 relativisation operator, allowing one to restrict
                 attention to a specific subtree while evaluating a
                 subexpression. We show that the expressive power of
                 this XPath dialect equals that of FO(MTC) for Boolean,
                 unary and binary queries. We also investigate the
                 complexity of the automata model as well as the XPath
                 dialect. We show that query evaluation be done in
                 polynomial time (combined complexity), but that
                 emptiness (or, satisfiability) is 2ExpTime-complete.",
  acknowledgement = ack-nhfb,
  articleno =    "18",
  fjournal =     "Journal of the ACM",
  journal-URL =  "",
  keywords =     "Transitive closure logic; tree automata; XPath",

  author =       "Steven J. Vaughan-Nichols",
  title =        "Will {HTML 5} Restandardize the {Web}?",
  journal =      j-COMPUTER,
  volume =       "43",
  number =       "4",
  pages =        "13--15",
  month =        apr,
  year =         "2010",
  CODEN =        "CPTRB4",
  DOI =          "",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Wed May 12 22:57:42 MDT 2010",
  bibsource =    "",
  acknowledgement = ack-nhfb,
  fjournal =     "Computer",
  journal-URL =  "",

  author =       "Michael Kohlhase and Florian Rabe",
  title =        "Semantics of {OpenMath} and {MathML 3}",
  journal =      j-MATH-COMPUT-SCI,
  volume =       "6",
  number =       "3",
  pages =        "235--260",
  month =        sep,
  year =         "2012",
  CODEN =        "????",
  DOI =          "",
  ISSN =         "1661-8270 (print), 1661-8289 (electronic)",
  ISSN-L =       "1661-8270",
  bibdate =      "Tue Nov 6 10:16:26 MST 2012",
  bibsource =    ";
  URL =          "",
  acknowledgement = ack-nhfb,
  fjournal =     "Mathematics in Computer Science",
  journal-URL =  "",

  author =       "C. Pozrikidis",
  title =        "{XML} in scientific computing",
  publisher =    pub-CRC,
  address =      pub-CRC:adr,
  pages =        "xv + 243 pages",
  year =         "2013",
  ISBN =         "1-4665-1227-X (hardback)",
  ISBN-13 =      "978-1-4665-1227-6 (hardback)",
  LCCN =         "Q183.9 .P69 2013",
  bibdate =      "Fri Nov 16 06:32:54 MST 2012",
  bibsource =    ";
  series =       "Chapman and Hall/CRC numerical analysis and scientific
                 computing series",
  acknowledgement = ack-nhfb,
  subject =      "XML (Document markup language); Science; Data
                 processing; Numerical analysis; COMPUTERS / Internet /
                 General.; MATHEMATICS / General.; MATHEMATICS / Number