A Structured Representation for Noun Phrases and Anaphora
نویسنده
چکیده
I present a computationally-based representation for inde nite noun phrases and anaphora that models their use in natural language. To this end, three goals for knowledge representation for natural language processing: natural form, conceptual completeness, and structure sharing are described. In addressing these goals, an augmentation to the representation of variables (corresponding to inde nite noun phrases or anaphora) so that variables are not atomic terms is suggested. This leads to an extended, more \natural" representation. It is shown how this representation resolves some representational di culties with sentences with nonlinear quanti er scoping, in particular, donkey sentences.
منابع مشابه
Comparing Domain-Specific and Non-Domain-Specific Anaphora Resolution Techniques
A quantification is provided for the improvements made in traditional salience-based pronominal anaphora resolution precision when input text that has been parsed using a large scale grammar to locate syntactic function of noun phrases, is used instead of input text where more shallow syntactic analysis techniques were used for identifying grammatical function. In addition, domain-specific tech...
متن کاملTowards a Generalization of Anaphora
This paper deals with anaphoric properties of both pronominal and nonpronominal Noun Phrases within the framework of Discourse Representation Theory (DRT). A generalized notion of anaphora is advocated, in which the notion of anaphora is extended to cover relations between anaphor and antecedent other than referential identity. This paper tries to make insights gained in DRT, as well as in othe...
متن کاملA Scalable, Empirical Approach to Anaphoric Reference
Most of the suggested solutions for the anaphora problem have been concerned with getting the correct answer in all situations. This means they must involve large amounts of syntactic, semantic and world knowledge, and therefore can only be applied to a limited scope of documents. These solutions do not scale well. We have designed and implemented a scalable heuristic approach to the anaphora p...
متن کاملAnaphora Resolution of Demonstrative Noun Phrases in Medline Abstracts
This paper reports our investigation of machine learning methods applied to anaphora resolution for Biology texts. Our primary concern is the investigation of features and their combinations for effective anaphora resolution. In this paper, we focus on the resolution of demonstrative anaphoric noun phrases. We propose several novel features that we call highlighting features and consider their ...
متن کاملCorpus - Based Identi cation of Non - Anaphoric NounPhrasesDavid
Coreference resolution involves nding antecedents for anaphoric discourse entities, such as deenite noun phrases. But many deenite noun phrases are not anaphoric because their meaning can be understood from general world knowledge (e.g., \the White House" or \the news media"). We have developed a corpus-based algorithm for automatically identifying deenite noun phrases that are non-anaphoric, w...
متن کامل