A rethink of the relationship between salience and anaphora resolution
نویسنده
چکیده
According to prior work on the interpretation of anaphoric elements, the form of linguistic expression used for reference to a discourse entity reflects the entity’s degree of salience. When both fully specified and underspecified forms of reference are available the most underspecified forms are used for reference to the most salient entity. In this paper, we present sentence completion data from Greek, a language whose range of anaphoric expressions includes null subjects and cliticized object pronouns (weak pronominals) as well as demonstrative expressions (strong pronominals). The results of our studies cast doubt on the currently assumed mapping between salience and form of linguistic expression. We found that discourse salience does not warrant the use of the most underspecified form (null subject) in Greek. Semantic focusing (Stevenson et al., 2000) may bring into focus an entity in an object (or other non-subject) position but the choice of antecedent for null or overt forms is senstive to syntactic properties of the antecedent. We argue that discourse salience and choice of referring expression can be sensitive to different properties of discourse entities which may or may not converge depending on the language.
منابع مشابه
A Fully-Lexicalized Probabilistic Model for Japanese Zero Anaphora Resolution
This paper presents a probabilistic model for Japanese zero anaphora resolution. First, this model recognizes discourse entities and links all mentions to them. Zero pronouns are then detected by case structure analysis based on automatically constructed case frames. Their appropriate antecedents are selected from the entities with high salience scores, based on the case frames and several pref...
متن کاملMachine Learning for Anaphora Resolution
We compare the performance of the Kennedy and Boguraev [12] anaphora resolution algorithm to the performance of a memory-based machine learning algorithm. For each pronoun, the machine learning algorithm is given the Kennedy and Boguraev feature set for a list of candidate antecedents, but it does not have access to the salience weights for the features. Nevertheless, a statistical analysis sho...
متن کاملFactors In Anaphora Resolution: They Are Not The Only Things That Matter - A Case Study Based On Two Different Approaches
The paper discusses the significance of factors in anaphora resolution and on the basis of a comparative study argues that what matters is not only a good set of reliable factors but also the strategy for their application. The objective of the study was to find out how well the same set of factors worked within two different computational strategies. To this end, we tuned two anaphora resoluti...
متن کاملPronominal and Sortal Anaphora Resolution for Biomedical Literature
Anaphora resolution is one of essential tasks in message understanding. In this paper resolution for pronominal and sortal anaphora, which are common in biomedical texts, is addressed. The resolution was achieved by employing UMLS ontology and SA/AO (subject-action/action-object) patterns mined from biomedical corpus. On the other hand, sortal anaphora for unknown words was tackled by using the...
متن کاملCooperation between Pronoun and Reference Resolution for Unrestricted Texts
Anaphora resolution is envisaged in this paper as part of the reference resolution process. A general open architecture is proposed, which can be particularized and configured in order to simulate some classic anaphora resolution methods. With the aim of improving pronoun resolution, the system takes advantage of elementary cues about characters of the text, which are represented through a part...
متن کامل