Anaphoric Inference in Expository Text: The Effects of Anaphora Type, Mention Order and Typicality of Antecedent
نویسنده
چکیده
Introduction Anaphora has an important function in text comprehension. The processes of anaphoric inference are to make local coherence among sentences. The coherence constructed from several variables (e.g. Lee, 1993). The first variable is an anaphora type: noun phrase, pronoun or ellipsis. Another variable is the properties of antecedents: syntactic, semantic, or pragmatic. Yet another variable is discourse contexts such as a topic, theme, or implicit reader’s knowledge. The main purpose of this study is to investigate how these variables contribute to anaphoric inference differentially in expository texts.
منابع مشابه
A Mention-Ranking Model for Abstract Anaphora Resolution
Resolving abstract anaphora is an important, but difficult task for text understanding. Yet, with recent advances in representation learning this task becomes a more tangible aim. A central property of abstract anaphora is that it establishes a relation between the anaphor embedded in the anaphoric sentence and its (typically non-nominal) antecedent. We propose a mention-ranking model that lear...
متن کاملAnaphora as an Indicator of Elaboration: A Corpus Study
entity anaphora abstrProp abstrCluster abstrEvType anaphora poss meronym holonym hasMember setMember bridging Figure 1: Sekimo hierarchy of anaphoric relations For cospecLink two sets of secondary relations exist: one set for relations with antecedents of nominal type and one set for abstract entity anaphora. The subtypes of abstract entity anaphora are characterised as follows: abstrProp descr...
متن کاملAnaphora Resolution Involving Interactive Knowledge Acquisition
Anaphora resolution in current computer-processable controlled natural languages relies mainly on syntactic information, accessibility constraints and the distance of the anaphoric expression to its antecedent. This design decision has the advantage that a text can be processed automatically without any additional ontological knowledge, but it has the disadvantage that the author is severely re...
متن کاملImproved Best-First Clustering for Coreference Resolution in Indian Classical Music Forums
Clustering step in the mention-pair paradigm for coreference resolution, forms the chain of coreferent mentions from the mention pairs classified as coreferent. Clustering methods including best-first clustering considers each antecedent candidate individually, while selecting the antecedent for an anaphoric mention. Here we introduce an easyto-implement modification to best-first clustering to...
متن کاملAutomatic Recognition of French Expletive Pronoun Occurrences
We present a tool, called ILIMP, which takes as input a raw text in French and produces as output the same text in which every occurrence of the pronoun il is tagged either with tag [ANA] for anaphoric or [IMP] for impersonal or expletive. This tool is therefore designed to distinguish between the anaphoric occurrences of il, for which an anaphora resolution system has to look for an antecedent...
متن کامل