We propose a new method for using anaphoric information in Latent Semantic Analysis (lsa), and discuss its application to develop an lsa-based summarizer which achieves a significantly better performance than a system not using anaphoric information, and a better performance by the rouge measure than all but one of the single-document summarizers participating in duc-2002. Anaphoric information...

This paper presents a system which intends to resolve anaphora in the framework of the Discourse Representation Theory, arrd using a lexicon-grammar of anaphoric verbs, through the application of selection criteria for assignment of a referent to an anaphora. From a semantic representation of text provided by a DRT system implemented in Prolog, the system uses several criteria of selection of r...

A distribution of anaphoric elements roughly like that found in English occurs in languages around the world: There are certain lexical items that occur only with antecedents which ccommand them and which are located in the same local domain (roughly, clause) as the anaphoric elements. In contrast, other anaphoric elements are unable to take c-commanding antecedents within the local domain. The...

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...

This study investigates the effects of variation in anaphoric form by comparing the processing and interpretation of a null VP-anaphoric phrase (i.e. did too) and an overt VP-anaphoric phrase (e.g. did it too) in contexts where both forms are grammatical. Unification theories predict that in contexts involving a highly accessible antecedent, participants prefer the least informative grammatical...

The computational model in present paper confirms that memory-based accounts are sufficient to account for a high rate of success at first-pass referent retrieval for anaphoric (and non-anaphoric) nouns. Because even definite noun phrases can often be non-anaphoric (e.g., Poesio & Vieira, 1998), an adequate model must account for how a reader makes an explicit or implicit decision about the ana...