... logical rules fora fragment of the semantic interpretation (and plan recognition) process. The four simple rules we gave already capture a wide variety of semantic and pragmatic phenomena. ... This has the effect. of concentrating all knowledge about all of an object's names as facts about the best name. Frail will take as input a simple frame representation and translate it ... rule of case relations. Formally, it says that for all syntactic positional relations and all meanings of the head, there must exist a case relation which is the significance of that syntactic...
... Zbinden, Alan McNaught,Rafael Alc´antara, Michael Darsow, Micka¨el Guedj,and Michael Ashburner. 2008. ChEBI: a databaseand ontology for chemical entities of biologicalinterest. Nucleic Acids ... transformsyntactic as well as morphological variations ofnames into a normalized name form. Basic trans-formations can be achieved via pattern match-ing (regular expressions) while for more com-plex ... a major goal of BioNLP is to automatically supporthumans by means of research in the area of infor-mation retrieval, data mining and information ex-traction. Term identification is of great...
... Krugler,Wayne Ward, James H. Martin, and Daniel Juraf-sky. 200 5a. Support vector learning for semantic argument classification. Machine Learning Journal.Sameer Pradhan, Wayne Ward, Kadri Hacioglu, JamesMartin, ... arguments,Arg0 is the Agent, Arg1 is Patient, etc. ArgM-may indicate adjunct arguments, such as Locative,Temporal.Many researchers (Gildea and Jurafsky, 2002;Pradhan et al., 200 5a) use feature-based ... Predicate Argument Feature spacenecessity of syntactic parsing forsemantic role la-beling. However, the standard flat features cannotmodel the syntactic information well. A predicate-argument...
... Martin, and Dan Jurafsky.200 5a. Support vector learning forsemantic argu-ment classification. Machine Learning, 60(1):11–39.Sameer Pradhan, Wayne Ward, Kadri Hacioglu, JamesMartin, and Daniel ... to automatically create an annotated corpus in a new language. Although these data are typicallyquite noisy, they have been used to train automaticsystems. For the particular case of transfer ... 29(1):19–51.Sebastian Padó and Mirella Lapata. 2005. Cross-lingual projection of role -semantic information. InProceedings of HLT/EMNLP 2005.Sameer Pradhan, Kadri Hacioglu, Valerie Krugler,Wayne Ward, James...
... redundant information. Hence, we will show how to annotate a syntax tree so that various interpretations can be characterized differently. Semantic Tagging A popular linguistic approach to annotate ... R&D Road II, Science-Based Industrial Park Hsinchu, TAIWAN 30077, R.O.C. ABSTRACT In natural language processing, ambiguity res- olution is a central issue, and can be regarded as a ... mantic score measure shows substantial im- provement in structural disambiguation over a syntax-based approach. 1. Introduction In a large natural language processing system, such as a machine...
... especially those in thenarrative domain. Users can create for- mal propositions to represent spans of text,as well as temporal relations and otheraspects of narrative. A built-in natural-language ... is that a modelwith a wider scope is more challenging for anno-tators. For example, part-of-speech tagging is aneasier task than PropBank annotation. We believethat careful user interface ... (equivalent toFigure 2) as configured fora particular Aesopfable.3. The procedure for reading a text for impor-tant named entities, and formally declaringthese named entities for the story graph.4....
... statistical machine translation ( SMT)community as a way of formalizing syntax-basedtranslation models between natural languages (NL).In generating multiple parse trees in a single deriva-tion, ... parsing is cast as a machine translation task,where an SCFG is used to model the translationof an NL into a formal meaning-representation lan-guage (MRL). Our algorithm, WASP, uses statisticalmodels ... logical forms are in-volved. For example, it should be straightforwardto adapt λ-WASP to the NL generation task—allone needs is a decoder that can handle input logicalforms. Other tasks that...
... desirable.FrameNet as a resource forsemantic role an-notation. Above, we have asked about the suitabil-ity of FrameNet forsemantic role annotation, andour data allow a first, though tentative, ... Extensive Semantic AnnotationKatrin Erk and Andrea Kowalski and Sebastian Pad´o and Manfred PinkalDepartment of Computational LinguisticsSaarland UniversitySaarbr¨ucken, Germany{erk, kowalski, ... suit-able resource as annotation basis. FrameNet roles,which are local to particular frames (abstract sit-uations), may be better suited for the annotationtask than the “classical” thematic...
... 2012.c2012 Association for Computational Linguistics A platform for collaborative semantic annotationValerio Basile and Johan Bos and Kilian Evang and Noortje Venhuizen{v.basile,johan.bos,k.evang,n.j.venhuizen}@rug.nlCenter ... IntroductionData-driven approaches in computational seman-tics are still rare because there are not manylarge annotated resources that provide empiri-cal information about anaphora, presupposition,scope, ... Venhuizen{v.basile,johan.bos,k.evang,n.j.venhuizen}@rug.nlCenter for Language and Cognition Groningen (CLCG)University of Groningen, The NetherlandsAbstractData-driven approaches in computationalsemantics are not common because thereare only few semantically...
... over baseline), particularly given that, in addition to the manual reference answer facet representation, an automatically extracted approximation of the rep-resentation was a key factor in ... test examples, assigning a Table 1 label for each reference answer facet. We used a variety of linguistic features that as-sess the facets’ similarity via lexical entailment probabilities ... dependency parses are used to align the terms and facet-level information for feature extraction. Remaining details can be found in (Nielsen et al., 200 8a) and are not central to the semantic representation...
... Sameer Pradhan, Kadri Hacioglu, Valeri Krugler, Wayne Ward, James H. Martin and Daniel Jurafsky. 200 5a. Support vector learning forsemantic argument classi-fication. Journal of Machine Learning ... Sameer Pradhan, Wayne Ward, Kadri Hacioglu, James Martin and Daniel Jurafsky. 2005b. Semantic role la-beling using different syntactic views. ACL-2005 Vasin Punyakanok, Dan Roth, Wen-tau ... feature selection for Natu-ral Language processing tasks. ACL-2004 Vladimir N. Vapnik. 1998. Statistical Learning Theory. Wiley Nianwen Xue and Martha Palmer. 2004. Calibrating features for...