%
% GENERATED FROM https://www.coli.uni-saarland.de
%    by   : anonymous
%    IP   : coli2006.lst.uni-saarland.de
%    at   : Mon, 05 Feb 2024 15:42:10 +0100 GMT
%    
% Selection : Author: Paul_Buitelaar
%




@InProceedings{Bos_et_al:1995,
      AUTHOR = {Bos, Johan and Buitelaar, Paul and Mineur, Anne-Marie},
      TITLE = {Bridging as Coercive Accomodation},
      YEAR = {1995},
      BOOKTITLE = {Computational Logic for Natural Language Processing (CLNLP '95) - Workshop Proceedings, April 3-5},
      EDITOR = {Manandhar, Suresh},
      ADDRESS = {South Queensferry, Scotland},
      URL = {http://www.elsnet.org/publications/clnlp95/Bos-Mineur.ps.gz},
      NOTE = {A shorter version also appeared in the Lecture Notes of a workshop on The Computational Lexicon, at the 6th ESSLLI, Barcelona 1995},
      ANNOTE = {COLIURL : Bos:1995:BCAa.pdf Bos:1995:BCAa.ps}
}

@InProceedings{Bos_et_al:1995_1,
      AUTHOR = {Bos, Johan and Buitelaar, Paul and Mineur, Anne-Marie},
      TITLE = {Bridging as Coercive Accomodation},
      YEAR = {1995},
      BOOKTITLE = {6th European Summer School in Logic, Language, and Information (ESSLLI'95). Workshop on The Computational Lexicon, August 13-25},
      ADDRESS = {Barcelona, Spain}
}

@TechReport{Bos_et_al:1995_2,
      AUTHOR = {Bos, Johan and Mineur, Anne-Marie and Buitelaar, Paul},
      TITLE = {Bridging as Coercive Accomodation},
      YEAR = {1995},
      MONTH = {March},
      NUMBER = {52},
      ADDRESS = {Saarbrücken},
      TYPE = {CLAUS-Report},
      INSTITUTION = {Universität des Saarlandes},
      URL = {ftp://ftp.coli.uni-sb.de/pub/coli/claus/claus52.ps},
      ABSTRACT = {This paper combines insights from Pustejovsky's GL theory with Van der Sandt's anaphora resolution algorithm. The phenomenon of bridging is accounted for in terms of linking anaphoric expressions to information that can be inferred from the lexical semantic knowledge that is stored in lexical entries. In doing so, we can distinguish between the normal linking cases as in (1), the special cases of coercive accommodation as in (2) and the bottom cases of accommodation as in (3). (1) When I call a barkeeper, the barkeeper never comes. (2) When I go to a bar, the barkeeper always throws me out. (3) When I came in, the barkeeper said hello.},
      ANNOTE = {COLIURL : Bos:1995:BCAc.pdf Bos:1995:BCAc.ps}
}

@InProceedings{Buitelaar:1998,
      AUTHOR = {Buitelaar, Paul},
      TITLE = {The Acquisition of Defaults in Lexical Semantic Representations},
      YEAR = {1998},
      BOOKTITLE = {Workshop on Lexical Semantic Systems (WLSS '98), April 6-7},
      ADDRESS = {Pisa, Italy},
      URL = {http://dfki.de/~paulb/wlss98.ps.gz},
      ABSTRACT = {The paper defends the notion that semantic tagging should be viewed as more than disambiguation between senses. Instead, semantic tagging should be a first step in the interpretation process by assigning each lexical item a representation of all of its systematically related senses, from which further semantic processing steps can derive discourse dependent interpretations. This leads to a new type of semantic lexicon (CoreLex ) that supports underspecified semantic tagging through a design based on systematic polysemous classes and a class-based acquisition of lexical knowledge for specific domains.},
      ANNOTE = {COLIURL : Buitelaar:1998:ADL.pdf Buitelaar:1998:ADL.ps}
}

@InProceedings{Buitelaar:1998_1,
      AUTHOR = {Buitelaar, Paul},
      TITLE = {Specification and Underspecification in Lexical Semantic Processing for Information Extraction},
      YEAR = {1998},
      BOOKTITLE = {Bad Teinach Workshop on Underspecification, May},
      ADDRESS = {Bad Teinach, Germany},
      URL = {http://dfki.de/~paulb/teinach.ps.gz},
      ABSTRACT = {The work reported here is part of a research effort to extend an existing information extraction system (SMES) with more sophisticated lexical semantic capabilities, including the use of underspecified representations, in order to make the important step of domain modelling, in porting the system to different application areas, more systematic and generally to increase the accuracy of the system. In general, information extraction (IE) is a rather scaled down version of natural language understanding, in which there is little room for the processing of deep (i.e. lexical semantic) knowledge. However, in obvious ways, underspecified lexical semantic representations can be seen as shallow lexical meanings that have a similar status as chunks in syntactic processing. Therefore, the use of such representations in IE seems an attractive option to extend the semantic capabilities of these systems, although it is not entirely clear where underspecification will be useful and where not. It is the topic of this paper to investigate this into some respect.},
      ANNOTE = {COLIURL : Buitelaar:1998:SUL.pdf Buitelaar:1998:SUL.ps}
}

@InProceedings{Buitelaar:1998_2,
      AUTHOR = {Buitelaar, Paul},
      TITLE = {CoreLex: An Ontology of Systematic Polysemous Classes},
      YEAR = {1998},
      BOOKTITLE = {Proceedings of the 1st International Conference on Formal Ontology in Information Systems (FOIS'98), June 6-8},
      VOLUME = {46},
      PAGES = {221-235},
      EDITOR = {Guarino, Nicola},
      SERIES = {Frontiers in Artificial Intelligence and Applications},
      ADDRESS = {Trento, Italy},
      PUBLISHER = {IOS Press},
      URL = {http://dfki.de/~paulb/fois98.ps.gz},
      ABSTRACT = {This paper is concerned with a unified approach to the systematic polysemy and underspecification of nouns. Systematic polysemy -- senses that are systematically related and therefore predictable over classes of lexical items -- is fundamentally different from homonymy -- senses that are unrelated, non-systematic and therefore not predictable. At the same time, studies in discourse analysis show that lexical items are often left underspecified for a number of related senses. Clearly, there is a correspondence between these phenomena, the investigation of which is the topic of this paper. Acknowledging the systematic nature of polysemy and its relation to underspecified representations, allows one to structure ontologies for lexical semantic processing more efficiently, generating more appropriate interpretations within context. In order to achieve this, one needs a thorough analysis of systematic polysemy and underspecification on a large and useful scale. The paper establishes an ontology and semantic database (CoreLex) of 126 semantic types, covering around 40,000 nouns and defining a large number of systematic polysemous classes that are derived by a careful analysis of sense distributions in WordNet. The semantic types are underspecified representations based on generative lexicon theory.},
      ANNOTE = {COLIURL : Buitelaar:1998:COS.pdf Buitelaar:1998:COS.ps}
}

@InProceedings{Buitelaar:1999,
      AUTHOR = {Buitelaar, Paul},
      TITLE = {Ambiguity in Semantic Annotation Submitted},
      YEAR = {1999},
      BOOKTITLE = {Standardizing Lexical Resources Workshop (SIGLEX '99), June 21-22},
      ADDRESS = {University of Maryland College Park, USA}
}

@InProceedings{Buitelaar:2000,
      AUTHOR = {Buitelaar, Paul},
      TITLE = {Reducing Lexical Semantic Complexity with Systematic Polysemous Classes and Underspecification},
      YEAR = {2000},
      BOOKTITLE = {Workshop on Syntactic and Semantic Complexity in Natural Language Processing Systems (ANLP-NAACL'00), April 29 - May 3},
      EDITOR = {Bagga, Amit and Pustejovsky, James and Zadrozny, Wlodek},
      ADDRESS = {Seattle, Washington, USA},
      URL = {ftp://lt-ftp.dfki.uni-sb.de/pub/papers/local/anlp00.ps. http://dfki.de/~paulb/anlp00.ps},
      ABSTRACT = {This paper presents an algorithm for finding systematic polysemous classes in WordNet and similar semantic databases, based on a definition in (Apresjan 1973). The introduction of systematic polysemous classes can reduce the amount of lexical semantic processing, because the number of disambiguation decisions can be restricted more clearly to those cases that involve real ambiguity (homonymy). In many applications, for instance in document categorization, information retrieval, and information extraction, it may be sufficient to know if a given word belongs to a certain class (underspecified sense) rather than to know which of its (related) senses exactly to pick. The approach for finding systematic polysemous classes is based on that of (Buitelaar 1998a, Buitelaar 1998b), while addressing some previous shortcomings.},
      ANNOTE = {COLIURL : Buitelaar:2000:RLS.pdf Buitelaar:2000:RLS.ps}
}

@InProceedings{Buitelaar:2001,
      AUTHOR = {Buitelaar, Paul},
      TITLE = {The SENSEVAL-II Panel on Domains, Topics and Senses},
      YEAR = {2001},
      BOOKTITLE = {Proceedings of the 2nd International Workshop on Evaluating Word Sense Disambiguation Systems (SENSEVAL-II)},
      ADDRESS = {Toulouse},
      URL = {http://dfki.de/~paulb/senseval2.ps},
      ABSTRACT = {An important aspect of sense disambiguation is the wider semantic space (domain, topic) in which the ambiguous word occurs. This may be most clearly illustrated by some cross-lingual examples, as they would appear in (machine) translation. Consider for instance the English word housing. In a more general 'sense', this translates in German into Wohnung. In an engineering setting however it translates into Gehaeuse. Also verbs may be translated differently (i.e. have a different sense) according to the semantic space in which they occur. For instance, English warming up translates into erhitzen in a more general sense, but into aufwaermen in the sports domain. Because of the apparent relevance then of domains or topics on sense disambiguation, a panel was organized at SENSEVAL-2 to discuss some current and previous work in this area. The paper presents a more extended overview based on the relevant literature, besides giving a summary of the discussion that developed after the panel presentations.},
      ANNOTE = {COLIURL : Buitelaar:2001:SIP.pdf Buitelaar:2001:SIP.ps}
}

@InProceedings{Buitelaar:2002,
      AUTHOR = {Buitelaar, Paul},
      TITLE = {Lexical Semantics in the Age of the Semantic Web – Invited Talk},
      YEAR = {2002},
      BOOKTITLE = {Proceedings of the Conference of the Slovenian Society for Language Technologies, 14 - 15th October 2002},
      PAGES = {6 - 10},
      EDITOR = {Erjavec, Tomaz and Gros, Jerneja},
      ADDRESS = {Ljubljana, Slovenia},
      URL = {http://dfki.de/~paulb/sdjt02.ps},
      ABSTRACT = {Lexical semantics is the study of word meaning. The semantic web is a vision of what the web could be if it would foremost consist of knowledge (structured data) rather than text or other unstructured data as it is today. This paper is about the future of word meaning if the semantic web becomes a reality. First, I will therefore briefly clarify what the semantic web vision consists of, followed by a sketch of lexical semantics. Finally, I will speculate on how the inherent semantic standardization process of the semantic web could have a dramatic influence on the study and use of word meaning.},
      ANNOTE = {COLIURL : Buitelaar:2002:LSA.pdf}
}

@InProceedings{Buitelaar_et_al:2001,
      AUTHOR = {Buitelaar, Paul and Alexandersson, Jan and Jaeger, Tilman and Lesch, Stephan and Pfleger, Norbert and Raileanu, Diana and von den Berg, Tanja and Klöckner, Kerstin and Neis, Holger and Schlarb, Hubert},
      TITLE = {An Unsupervised Semantic Tagger Applied to German},
      YEAR = {2001},
      BOOKTITLE = {Proceedings of the 3rd Conference on Recent Advances in Natural Language Processing (RANLP'01), September 5-7},
      ADDRESS = {Tzigov Chark, Bulgaria},
      URL = {ftp://lt-ftp.dfki.uni-sb.de/pub/papers/local/ranlp01.ps ftp://lt-ftp.dfki.uni-sb.de/pub/papers/local/ranlp01.pdf http://dfki.de/~paulb/ranlp01.pdf},
      ABSTRACT = {We describe an unsupervised semantic tagger, applied to German, but which could be used with any language for which a corresponding XNet (WordNet, GermaNet, e tc.), POS tagger and morphological analyzer are available. Disambiguation is per formed by comparing co-occurrence weights on pairs of semantic classes (synsets from GermaNet). Precision is around 67% at a recall of around 65% (for all ambig uous words -- 81% for all words at a recall of 80%). Our results show the influe nce of context size and of semantic class frequency in the training corpus.},
      ANNOTE = {COLIURL : Buitelaar:2001:UST.pdf Buitelaar:2001:UST.ps}
}

@Proceedings{Paul_Koiti:2000,
      TITLE = {Proceedings of the COLING '00 Workshop on Semantic Annotation and Intelligent Content, August 5-6},
      YEAR = {2000},
      EDITOR = {Buitelaar, Paul and Hasida, Koiti},
      ADDRESS = {Luxembourg, Centre Universitaire},
      URL = {http://dfki.de/~paulb/coling2000.proceedings.pdf},
      ABSTRACT = {SEMANTIC ANNOTATION is augmentation of data to facilitate automatic recognition of the underlying semantic structure. A common practice in this respect is labeling of documents with thesaurus classes for the sake of document classification and management. In the medical domain, for instance, there is a long-standing tradition in terminology maintenance and annotation/classification of documents using standard coding systems such as ICD, MeSH and the UMLS meta-thesaurus. Semantic annotation in a broader sense also addresses document structure (title, section, paragraph, etc.), linguistic structure (dependency, coordination, thematic role, co-reference, etc.), and so forth. In NLP, semantic annotation has been used in connection with machine-learning software trainable on annotated corpora for parsing, word-sense disambiguation, co-reference resolution, summarization, information extraction, and other tasks. A still unexplored but important potential of semantic annotation is that it can provide a common I/O format through which to integrate various component technologies in NLP and AI such as speech recognition, parsing, generation, inference, and so on. INTELLIGENT CONTENT is semantically structured data that is used for a wide range of content-oriented applications such as classification, retrieval, extraction, translation, presentation, and question-answering, as the organization of such data provides machines with accurate semantic input to those technologies. Semantically annotated resources as described above are typical examples of intelligent content, whereas another major class includes electronic dictionaries and inter-lingual or knowledge-representation data. Some ongoing projects along these lines are GDA (Global Document Annotation), UNL (Universal Networking Language) and SHOE (Simple HTML Ontology Extension), all of which aim at motivating people to semantically organize electronic documents in machine-understandable formats, and at developing and spreading content-oriented application technologies aware of such formats. Along similar lines, MPEG-7 is a framework for semantically annotating audiovisual data for the sake of content-based retrieval and browsing, among others. Incorporation of linguistic annotation into MPEG-7 is in the agenda, because linguistic descriptions already constitute a main part of existing metadata. In short, semantic annotation is a central, basic technology for intelligent content, which in turn is a key notion in systematically coordinating various applications of semantic annotation. In the hope of fueling some of the developments mentioned above and thus promoting the linkage between basic researches and practical applications, the workshop invites researchers and practitioners from such fields as computational linguistics, document processing, terminology, information science, and multimedia content, among others, to discuss various aspects of semantic annotation and intelligent content in an interdisciplinary way.},
      ANNOTE = {COLIURL : Buitelaar:2000:PCW.pdf}
}

@InProceedings{Buitelaar_Mineur:1994,
      AUTHOR = {Buitelaar, Paul and Mineur, Anne-Marie},
      TITLE = {Coercion and Compositionality in Categorial Grammar},
      YEAR = {1994},
      BOOKTITLE = {9th Amsterdam Colloquium},
      PAGES = {175-188},
      EDITOR = {Dekker, Paul and Stokhof, Martin},
      ADDRESS = {Amsterdam},
      PUBLISHER = {Institute for Logic, Language and Computation},
      URL = {Full text in postscript gzipped http://dfki.de/~paulb/ac93.ps.gz},
      ANNOTE = {COLIURL : Buitelaar:1994:CCC.pdf Buitelaar:1994:CCC.ps}
}

@InProceedings{Buitelaar_et_al:1998,
      AUTHOR = {Buitelaar, Paul and Netter, Klaus and Xu, Feiyu},
      TITLE = {Integrating Different Strategies in Cross-Language Information Retrieval in the MIETTA Project},
      YEAR = {1998},
      BOOKTITLE = {Proceedings of the 14th Twente Workshop on Language Technology (TWLT 14). Language Technology in Multimedia Information Retrieval, December 7-8},
      PAGES = {9-17},
      EDITOR = {Hiemstra, Djoerd and de Jong, Franciska and Netter, Klaus},
      ADDRESS = {Enschede, The Netherlands},
      URL = {ftp://lt-ftp.dfki.uni-sb.de/pub/papers/local/kn-twlt14-98.pdf},
      ABSTRACT = {In this paper we describe an integrated approach to cross-language retrieval within the MIETTA project, whose objective is to build a special purpose search engine in the tourism domain that covers information from a number of geographical regions. MIETTA is designed to enable users to search and retrievegeographical regions. MIETTA is designed to enable users to search and retrieve information on the regions covered in their own language preferably. In order to facilitate the user with such functionality, the system includes document translation, cross-language query translation, multilingual generation from information extraction templates and document classification. In addition, query expansion is offered to identify proper query translation and enable template matching for information extraction purposes.},
      ANNOTE = {COLIURL : Buitelaar:1998:IDS.pdf}
}

@InProceedings{Buitelaar_Sacaleanu:2001,
      AUTHOR = {Buitelaar, Paul and Sacaleanu, Bogdan},
      TITLE = {Ranking and Selecting Synsets by Domain Relevance},
      YEAR = {2001},
      BOOKTITLE = {Proceedings of the WordNet and Other Lexical Resources: Applications, Extensions and Customizations. NAACL Workshop},
      ADDRESS = {Pittsburgh},
      URL = {http://dfki.de/~paulb/lexres.pdf},
      ABSTRACT = {The paper presents a novel method for domain specific sense assignment. The method determines the domain specific relevance of GermaNet synsets on the basis of the relevance of their constituent terms that co-occur within representative domain corpora. The approach is task independent and completely automatic. Experiments show results on three selected domains: business, soccer and medical.},
      ANNOTE = {COLIURL : Buitelaar:2001:RSS.pdf}
}

@InProceedings{Buitelaar_Sacaleanu:2002,
      AUTHOR = {Buitelaar, Paul and Sacaleanu, Bogdan},
      TITLE = {Extending Synsets with Medical Terms},
      YEAR = {2002},
      BOOKTITLE = {Proceedings of the 1st International WordNet Conference, January 21-25},
      ADDRESS = {Mysore, India},
      URL = {http://dfki.de/~paulb/gwa.pdf},
      ABSTRACT = {An important problematic issue with general semantic lexicons like WordNet or GermaNet is that they do not cover many terms and concepts specific to certain domains. Therefore, these resources need to be tuned to a specific domain at hand. This involves selecting those senses that are most appropriate for the domain, as well as extending the sense inventory with novel terms and novel senses that are specific to the domain. In this paper we focus on extending GermaNet synsets with domain specific terms, taking into account the domain relevance of senses (i.e. synsets).},
      ANNOTE = {COLIURL : Buitelaar:2002:ESM.pdf}
}

@InCollection{Mineur_Buitelaar:1995,
      AUTHOR = {Mineur, Anne-Marie and Buitelaar, Paul},
      TITLE = {A Compositional Treatment of Polysemous Arguments in Categorial Grammar},
      YEAR = {1995},
      BOOKTITLE = {Semantic Ambiguity and Underspecification},
      EDITOR = {van Deemter, Kees and Peters, Stanley},
      ADDRESS = {Stanford},
      PUBLISHER = {CSLI Publications}
}

@TechReport{Mineur_Buitelaar:1995_1,
      AUTHOR = {Mineur, Anne-Marie and Buitelaar, Paul},
      TITLE = {A Compositional Treatment of Polysemous Arguments in Categorial Grammar},
      YEAR = {1995},
      MONTH = {January},
      NUMBER = {49},
      PAGES = {19},
      ADDRESS = {Saarbrücken},
      TYPE = {CLAUS-Report},
      INSTITUTION = {Universität des Saarlandes},
      URL = {ftp://ftp.coli.uni-sb.de/pub/coli/claus/claus49.ps},
      ABSTRACT = {We discuss the extension of the standard logical rules (functional application and abstraction) in Categorial Grammar, in order to deal with some specific cases of polysemy. We borrow from Generative Lexicon theory which proposes the mechanism of coercion next to a rich nominal lexical semantic structure called qualia structure. In a previous paper we introduced coercion into the framework of sign-based Categorial Grammar and investigated its impact on traditional Fregean compositionality. In this paper we will elaborate on this idea, mostly working towards the introduction of a new semantic dimension. Where in current versions of sign-based Categorial Grammar only two representations are derived: a prosodic one (form) and a logical one (modelling), here we introduce also a more detailed representation of the lexical semantics. This extra knowledge will serve to account for linguistic phenomena like metonymy.},
      ANNOTE = {COLIURL : Mineur:1995:CTPb.pdf Mineur:1995:CTPb.ps}
}

@InProceedings{Raileanu_et_al:2002,
      AUTHOR = {Raileanu, Diana and Buitelaar, Paul and Vintar, Spela and Bay, Jörg},
      TITLE = {Evaluation Corpora for Sense Disambiguation in the Medical Domain},
      YEAR = {2002},
      BOOKTITLE = {Proceedings of the 3rd International Conference on Language Resources and Evaluation (LREC'02), May 29-31},
      ADDRESS = {Las Palmas, Canary Islands, Spain},
      URL = {http://dfki.de/~paulb/lrec2002.eval.ps http://www.dfki.de/dfkibib/publications/docs/lrec2002.eval.final.pdf http://www2.arnes.si/~svinta/lrec2002.eval.final.pdf},
      ABSTRACT = {An important aspect of word sense disambiguation is the evaluation of different methods and parameters. Unfortunately, there is a lack of test sets for evaluation, specifically for languages other than English and even more so for specific domains like medicine. Given that our work focuses on English as well as German text in the medical domain, we had to develop our own evaluation corpora in order to test our disambiguation methods. In this paper we describe the work on developing these corpora, using GermaNet and UMLS as (lexical) semantic resources, next to a description of the annotation tool KiC that we developed for support of the annotation task.},
      ANNOTE = {COLIURL : Raileanu:2002:ECS.pdf Raileanu:2002:ECS.ps}
}

@InProceedings{Ripplinger_et_al:2002,
      AUTHOR = {Ripplinger, Bärbel and Vintar, Spela and Buitelaar, Paul},
      TITLE = {Cross-Lingual Information Retrieval through Semantic Annotation},
      YEAR = {2002},
      BOOKTITLE = {Proceedings of the Workshop on Natural Language Processing in Biomedical Applications (NLPBA'02), March 8-9},
      ADDRESS = {Nicosia, Cyprus},
      URL = {http://dfki.de/~paulb/nlpba.ps},
      ABSTRACT = {We present a framework for concept-based, cross-lingual information retrieval (CLIR) in the medical domain, which is under development in the MUCHMORE project. Our approach is based on using the Unified Medical Language System (UMLS) as the primary source of semantic data, whereby documents and queries are annotated with multiple layers of linguistic information. Linguistic processing includes POS-tagging, morphological analysis, phrase recognition and the identification of medical concepts and semantic relations between them. The paper describes experiments in mono- and bilingual document retrieval, performed on a parallel English-German corpus of medical abstracts. Results show on the one hand that linguistic processing, especially lemmatisation and compound analysis, is a crucial step to achieving good baseline performance. On the other hand we show that semantic information, specifically the combined use of concepts and relations, significantly increases performance in cross-lingual retrieval.},
      ANNOTE = {COLIURL : Ripplinger:2002:CLI.pdf Ripplinger:2002:CLI.ps}
}

@InProceedings{Vintar_et_al:2002,
      AUTHOR = {Vintar, Spela and Buitelaar, Paul and Ripplinger, Bärbel and Sacaleanu, Bogdan and Raileanu, Diana and Prescher, Detlef},
      TITLE = {An Efficient and Flexible Format for Linguistic and Semantic Annotation},
      YEAR = {2002},
      BOOKTITLE = {Proceedings of the 3rd International Conference on Language Resources and Evaluation (LREC'02), May 29-31},
      ADDRESS = {Las Palmas, Canary Islands, Spain},
      URL = {http://dfki.de/~paulb/lrec2002.dtd.ps http://www.dfki.de/dfkibib/publications/docs/lrec2002.dtd.final.pdf},
      ABSTRACT = {The paper describes an XML annotation format and tool developed within the MUCHMORE project. The annotation scheme was designed specifically for the purposes of Cross-Lingual Information Retrieval in the medical domain so as to allow both efficient and flexible access to layers of information. We use a parallel English-German corpus of medical abstracts and annotate it with linguistic information (tokenisation, part-of-speech tagging, lemmatisation and decomposition, phrase recognition, grammatical functions) as well as semantic information from various sources. The annotation of medical terms/concepts, semantic types and semantic relations is based on the Unified Medical Language System (UMLS). Additionally, we use EuroWordNet as a general-language resource in annotating word senses and to compare domain-specific and general language use. A major aim of the project is also to complement existing ontological resources by extracting new terms and new semantic relations. We present the annotation scheme, which is conceptually related to stand-off annotation, and describe our tool for automatic semantic annotation.},
      ANNOTE = {COLIURL : Vintar:2002:EFF.pdf Vintar:2002:EFF.ps}
}

@Article{Volk_et_al:2002,
      AUTHOR = {Volk, Martin and Ripplinger, Bärbel and Vintar, Špela and Buitelaar, Paul and Raileanu, Diana and Sacaleanu, Bogdan},
      TITLE = {Semantic Annotation for Concept-Based Cross-Language Medical Information Retrieval},
      YEAR = {2002},
      JOURNAL = {International Journal of Medical Informatics},
      VOLUME = {67},
      NUMBER = {1-3},
      PAGES = {97-112},
      URL = {http://dfki.de/~paulb/jmi.pdf},
      ABSTRACT = {We present a framework for concept-based cross-language information retrieval in the medical domain, which is under development in the MUCHMORE project. Our approach is based on using the Unified Medical Language System (UMLS) as the primary source of semantic data. Documents and queries are annotated with multiple layers of linguistic information. Linguistic processing includes part-of-speech tagging, morphological analysis, phrase recognition and the identification of medical terms and semantic relations between them. The paper describes experiments in monolingual and cross-language document retrieval, performed on a corpus of medical abstracts. Results show that linguistic processing, especially lemmatization and compound analysis for German, is a crucial step in achieving a good baseline performance. On the other hand, they show that semantic information, specifically the combined use of concepts and relations, increases the performance in monolingual and cross-language retrieval.},
      ANNOTE = {COLIURL : Volk:2002:SAC.pdf}
}

@InProceedings{Volk_et_al:2003,
      AUTHOR = {Volk, Martin and Vintar, Spela and Buitelaar, Paul},
      TITLE = {Ontologies in Cross-Language Information Retrieval},
      YEAR = {2003},
      BOOKTITLE = {Proceeding of the Workshop Ontologie-basiertes Wissensmanagement (WOW2003). Workshop auf der 2. Konferenz Professionelles Wissensmanagement - Erfahrungen und Visionen (WM2003), 2.-4. April 2003},
      ADDRESS = {Luzern, Schweiz}
}

@InProceedings{NeBuStDe2007,
      AUTHOR = {Nemrava, Jan and Buitelaar, Paul and Declerck, Thierry},
      TITLE = {Event Alignment for Cross-Media Feature Extraction in the Football Domain},
      YEAR = {2007},
      BOOKTITLE = {Proc. of the International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS), Santorini, Greece},
      VOLUME = {6},
      NOTE = {HU}
}

@InProceedings{NeBuDe2007,
      AUTHOR = {Nemrava, Jan and Buitelaar, Paul and Declerck, Thierry and Svatek, V. and Petrak, J. and Cobet, A. and Zeiner, H. and Sadlier, D. and O`Connor, N. and Simou, N. and Tzouvaras, V.},
      TITLE = {An Architecture for Mining Resources Complementary to Audio-Visual Streams},
      YEAR = {2007},
      BOOKTITLE = {Proceedings of KAMC - Knowledge Acquisition from Multimedia Content - workshop at SAMT07 (International Conference on Semantics And digital Media Technologies), CEUR Workshop Proceedings (Online)},
      VOLUME = { 253},
      NOTE = {HU}
}

@InCollection{PaPe2008,
      AUTHOR = {Pantel, Patrick and Pennacchiotti, Marco},
      TITLE = {Automatically harvesting and ontologizing semantic relations},
      YEAR = {2008},
      BOOKTITLE = {Ontology learning and population : bridging the gap between text and knowledge},
      VOLUME = {167},
      PAGES = {171-195},
      EDITOR = {Buitelaar, Paul and Cimiano, Philipp},
      SERIES = {Frontiers in artificial intelligence and applications},
      ADDRESS = {Amsterdam ; Berlin [u.a.]},
      PUBLISHER = {IOS Press},
      NOTE = {MP}
}

@InProceedings{BuDeNeSa2008,
      AUTHOR = {Buitelaar, Paul and Declerck, Thierry and Nemrava, Jan and Sadlier, D.},
      TITLE = {Cross-media semantic indexing in the soccer domain},
      YEAR = {2008},
      BOOKTITLE = {2008 International Workshop on Content-Based Multimedia Indexing : [6th] CBMI 2008 ; London, United Kingdom, 18 - 20 June 2008},
      PAGES = {296-301},
      ADDRESS = {Piscataway, NJ},
      ORGANIZATION = {IEEE Computer Center},
      NOTE = {HU}
}

@InProceedings{HaDeBuMo2008,
      AUTHOR = {Hayashi, Y. and Declerck, Thierry and Buitelaar, Paul and Monachini, Monica},
      TITLE = {Ontologies for a global language infrastructure},
      YEAR = {2008},
      BOOKTITLE = {Proceedings of the 1st International Conference on global interoperability for language resources : (ICGL-2008), January 9-11, 2008, Hong Kong, China},
      PAGES = {105-112},
      NOTE = {HU}
}

@InProceedings{NeBuSvDe2008,
      AUTHOR = {Nemrava, Jan and Buitelaar, Paul and Svatek, V. and Declerck, Thierry},
      TITLE = {Text mining support for semantic indexing and analysis of A/V streams},
      YEAR = {2008},
      BOOKTITLE = {OntoImage 2008 : 2nd Workshop on Language Resources for Content-Based Image Retrieval ; ELDA ; LREC 2008, Marrakech, Morocco, 2008},
      PAGES = {37-41},
      NOTE = {HU}
}

@InProceedings{DeBuNeSa2008,
      AUTHOR = {Declerck, Thierry and Buitelaar, Paul and Nemrava, Jan and Sadlier, D.},
      TITLE = {Towards cross-media feature extraction},
      YEAR = {2008},
      BOOKTITLE = {Multimedia information extraction : papers from the AAAI fall symposium ; [November 7 - 9, 2008, in Arlington, Virginia, USA],(Technical report / American Association for Artificial Intelligence : FS ; 2008, 5)},
      PAGES = {41-46},
      EDITOR = {Maybury, Mark},
      ADDRESS = {Menlo Park, Calif.},
      PUBLISHER = {AAAI Press},
      NOTE = {HU}
}

@InProceedings{OriCou2013,
      AUTHOR = {O'Riain, Sean and Coughlan, Barry and Buitelaar, Paul and Declerck, Thierry and Krieger, Hans-Ulrich and Marie-Thomas, Susan},
      TITLE = {Cross-lingual querying and comparison of linked financial and business data},
      YEAR = {2013},
      MONTH = {26-30 May},
      BOOKTITLE = {The semantic web: ESWC 2013 satellite events},
      PAGES = {242-247},
      EDITOR = {Cimiano, Philipp and Fernández, Miriam and Lopez, Vanessa and Schlobach, Stefan and Völker, Johanna},
      SERIES = {Lecture notes in computer science},
      ADDRESS = {Montpellier},
      PUBLISHER = {Springer},
      NOTE = {HU}
}

@InBook{GroDec2014,
      AUTHOR = {Gromann, Dagmar and Declerck, Thierry},
      TITLE = {A Cross-Lingual Correcting and Completive Method for Multilingual Ontology Labels},
      YEAR = {2014},
      MONTH = {August},
      BOOKTITLE = {Towards the Multilingual Semantic Web (Künstliche Intelligenz)},
      EDITOR = {Buitelaar, Paul and Cimiano, Philipp},
      ADDRESS = {Heidelberg},
      PUBLISHER = {Springer}
}