An Algorithm for Same-Sentence Pronominal Resolution

AAAI Conferences

Pronoun resolution is a vital part of the more general task of coreference resolution. The aim of coreference resolution is, given a natural language text, to discover the entities mentioned in it and the textual mentions of these entities. A coreference system must correctly identify the sets into which the mentions of the text must be clustered so that each set corresponds to a real-world or imagined entity. As a step in this process, the system has to detect pairs of mentions that are assumed to refer to the same entity with a certain confidence. When one of these mentions is a pronoun, the task is called pronominal resolution. In the following example, the pronoun its refers back to the named entity Dawn Capital (its'antecedent'): Dawn Capital changes its name. Previous work in pronominal resolution ranges from naive syntactic approaches to semantically rich approaches and from supervised to unsupervised learning.


Translation of Pronominal Anaphora between English and Spanish: Discrepancies and Evaluation

arXiv.org Artificial Intelligence

This paper evaluates the different tasks carried out in the translation of pronominal anaphora in a machine translation (MT) system. The MT interlingua approach named AGIR (Anaphora Generation with an Interlingua Representation) improves upon other proposals presented to date because it is able to translate intersentential anaphors, detect co-reference chains, and translate Spanish zero pronouns into English---issues hardly considered by other systems. The paper presents the resolution and evaluation of these anaphora problems in AGIR with the use of different kinds of knowledge (lexical, morphological, syntactic, and semantic). The translation of English and Spanish anaphoric third-person personal pronouns (including Spanish zero pronouns) into the target language has been evaluated on unrestricted corpora. We have obtained a precision of 80.4% and 84.8% in the translation of Spanish and English pronouns, respectively. Although we have only studied the Spanish and English languages, our approach can be easily extended to other languages such as Portuguese, Italian, or Japanese.


Translation of Pronominal Anaphora between English and Spanish: Discrepancies and Evaluation

AAAI Conferences

This paper evaluates the different tasks carried out in the translation of pronominal anaphora in a machine translation (MT) system. The MT interlingua approach named AGIR (Anaphora Generation with an Interlingua Representation) improves upon other proposals presented to date because it is able to translate intersentential anaphors, detect coreference chains, and translate Spanish zero pronouns into English--issues hardly considered by other systems. The paper presents the resolution and evaluation of these anaphora problems in AGIR with the use of different kinds of knowledge (lexical, morphological, syntactic, and semantic). The translation of English and Spanish anaphoric third-person personal pronouns (including Spanish zero pronouns) into the target language has been evaluated on unrestricted corpora. We have obtained a precision of 80.4% and 84.8% in the translation of Spanish and English pronouns, respectively. Although we have only studied the Spanish and English languages, our approach can be easily extended to other languages such as Portuguese, Italian, or Japanese.


Translation of Pronominal Anaphora between English and Spanish: Discrepancies and Evaluation

Journal of Artificial Intelligence Research

This paper evaluates the different tasks carried out in the translation of pronominal anaphora in a machine translation (MT) system. The MT interlingua approach named AGIR (Anaphora Generation with an Interlingua Representation) improves upon other proposals presented to date because it is able to translate intersentential anaphors, detect co-reference chains, and translate Spanish zero pronouns into English---issues hardly considered by other systems. The paper presents the resolution and evaluation of these anaphora problems in AGIR with the use of different kinds of knowledge (lexical, morphological, syntactic, and semantic). The translation of English and Spanish anaphoric third-person personal pronouns (including Spanish zero pronouns) into the target language has been evaluated on unrestricted corpora. We have obtained a precision of 80.4% and 84.8% in the translation of Spanish and English pronouns, respectively. Although we have only studied the Spanish and English languages, our approach can be easily extended to other languages such as Portuguese, Italian, or Japanese.


A Large Margin Approach to Anaphora Resolution for Neuroscience Knowledge Discovery

AAAI Conferences

A discriminative large margin classifier based approach to anaphora resolution for neuroscience abstracts is presented. The system employs both syntactic and semantic features. A support vector machine based word sense disambiguation method combining evidence from three methods, that use WordNet and Wikipedia, is also introduced and used for semantic features. The support vector machine anaphora resolution classifier with probabilistic outputs achieved almost four-fold improvement in accuracy over the baseline method.