Báo cáo khoa học: "Example-Based Metonymy Recognition for Proper Nouns" pot

... Example-Based Metonymy Recognition for Proper NounsYves PeirsmanQuantitative Lexicology and Variational Li n g u isticsUniversity of Leuven, Belgiumyves.peirsman@arts.kuleuven.beAbstract Metonymy recognition ... the ﬁeld of metonymy recog-nition.2 Example-based metonymy recognition As I have argued, Nissim and Markert’s (2003)approach to metonymy recognition is quite com-plex. I therefore wanted ... metonymical cate-gory they belonged to. For the country names,Markert and Nissim distinguished betweenplace -for- people, place -for- eventand place -for- product. For the organi-zation names, the most...

Báo cáo khoa học: "Named Entity Recognition for Catalan Using Spanish Resources" potx

... ofAdaBoost–based binary classifiers for recognizingthe Named Entities in running text. See (Carreraset al., 2002) for details.The NE recognition task is performed as a se-quence tagging problem ... case for minority languages withfew pre–existing linguistic resources and/or lim-ited funding possibilities.Our goal in this paper is to develop a low–costNamed Entity recognition system for ... about that NamedEntity Recognition and Classification (NERC) areNatural Language Processing tasks which may im-prove the performance of many applications, suchas Information Extraction, Machine...

Tài liệu Báo cáo khoa học: "A COMPUTATIONAL MECHANISM FOR PRONOMINAL REFERENCE" pot

... checked for minimality during a second. Since update-node is a general mechanism for adding or modifying information to a node on the basis of c-commanding constituents it is fairly straightforward ... algorithm explicitly indicates the potential antecedents of a personal pronoun. Again, this is more desirable than leaving this information implicit; besides the potential (and perhaps small) computa- ... representing antecedence information for personal pronouns contributes to this goal. In the next section, we show how our algorithm overcomes these limitations. 3. THE ALGORITHM Before giving the details...

Báo cáo khoa học: "SMS based Interface for FAQ Retrieval" pot

... to build in-formation based services around SMS technology.Today, a majority of SMS based information ser-vices require users to type speciﬁc codes to re-trieve information. For example to ... recently allowed users toformulate queries in natural language using SMS. For example, many contact centers now allow cus-tomers to “text” their complaints and requests for information over SMS. ... words with a high idf score.The rationale for this stems from the factthat queries, in general, are composed of in-formative words. Thus for example, for agiven SMS token “byk”, idf of “bike”...

Báo cáo khoa học: "A Common Framework for Syntactic Annotation" pot

... application-specific format could betranslated directly into the virtual AML, eliminating theneed for the intermediary concrete AML format. However,especially for existing formats, it is typically ... project-specific format, if desired.• Expansion structures: A project-specificformat may alter the structure of theannotation as expressed using the structuralskeleton. For example, it may be desirable for ... annotationschemes used in treebanks are often describedinformally in guidebooks for annotators,leaving considerable room for variation; for example, Charniak (1996) notes that the PTBimplicitly...

Báo cáo khoa học: "Mining the Web for Bilingual Text" pot

... world changes. For example, Diekema et al., in a presentation at the 1998 TREC-7 conference (Voorhees and Har- man, 1998), observed that the performance of their cross-language information retrieval ... STRA N D (Structural Translation Recognition for Acquiring Natural Data) designed to explore the Web as a source of parallel text, demon- strating its potential with a small-scale evalu- ... (Dunning, 1994). Although this does introduce a need for language-specific training data for the two languages under consideration, it is a very mild form of language dependence: Dunning and others...

Báo cáo khoa học: "Semantic Role Labeling for Coreference Resolution" pot

... SRL are pronouns and common nouns. On theother hand, SRL information has a limited or evenworsening effect on the performance on proper names, where features such as string matching andalias ... performance. Table 6 shows the per-formance variations obtained by leaving out eachfeature in turn. Again, it can be seen that remov-ing both I and JSEMROLE induces a relativelyhigh performance ... descriptive in-formation into the relations holding between re-ferring expressions (REs). This layer of semanticcontext abstracts from the speciﬁc lexical expres-sions used, and therefore represents...

Báo cáo khoa học: "Cognitively Motivated Features for Readability Assessment" pot

... were interested in information that would be re-levant to their daily lives. While for some ge-nres, human editors can prepare texts for these users, this is not practical for news sources that ... assessment for other groups of users. Acknowledgements We thank the Weekly Reader Corporation for making its corpus available for our research. We are grateful to Martin Jansche for his assistance ... of readers with particular reading difficulties. Other formulas rely on lexical information; e.g., the New Dale-Chall readability formula consults a static, manually-built list of “easy”...

Báo cáo khoa học: "Structural Correspondence Learning for Parse Disambiguation" pot

... Greece, 2 April 2009.c2009 Association for Computational LinguisticsStructural Correspondence Learning for Parse DisambiguationBarbara PlankAlfa-informaticaUniversity of Groningen, The Netherlandsb.plank@rug.nlAbstractThe ... need for domain adaptation arises in manyNLP tasks: Part-of-Speech tagging, SentimentAnalysis, Semantic Role Labeling or StatisticalParsing, to name but a few. For example, the per-formance ... Attribute Value Gram-mar (SAVG) for Dutch (van Noord and Malouf,2005; van Noord, 2006). For our empirical eval-1As shown in Dredze et al. (2007), the biggest problem for the shared task was that...

Báo cáo khoa học: "A Sentiment Analyzer for Micro-blogs" potx

... wordsused for lookup. The prediction for a tweet usesmajority vote-based approach as for version 1. Theoptimal POS bi-tags have been derived experimen-tally by using top 10% features on information ... is considered for in-version. The two versions of C-Feel-It vary in theirLexicon-based Sentiment Predictor. Figure 3 showsthe Lexicon-based Sentiment Predictor for version1. For each word ... for search string rnegscore[r] = Negative score for search string robjscore[r] = Objective score for search string rm = Number of resources used for predictionpi, ni, oi= Positive,negative...

Xem thêm