Robust pronoun resolution with limited knowledge

Abstract

Most traditional approaches to anaphora resolution rely heavily on linguistic and domain knowledge. One of the disadvantages of developing a knowledgebased system, however, is that it is a very labourintensive and time-consuming task. This paper presents a robust, knowledge-poor approach to resolving pronouns in technical manuals, which operates on texts pre-processed by a part-of-speech tagger. Input is checked against agreement and for a number of antecedent indicators. Candidates are assigned scores by each indicator and the candidate with the highest score is returned as the antecedent. Evaluation reports a success rate of 89.7% which is better than the success rates of the approaches selected for comparison and tested on the same data. In addition, preliminary experiments show that the approach can be successfully adapted for other languages with minimum modifications.

Improving LSA-based summarization with anaphora resolution

“…The current version of the system includes an implementation of the MARS pronoun resolution algorithm (Mitkov, 1998) and a partial implementation of the algorithm for resolving definite descriptions proposed by Vieira and Poesio (2000). The current version of GUITAR does not include methods for resolving proper nouns.…”

Evaluation-driven design of a robust coreference resolution system

“…Several of them illustrate knowledge-poor approaches, such as Harabagiu and Maiorano (1999), following pioneering work on pronoun resolution by Mitkov (1996Mitkov ( , 1998. Several of them illustrate knowledge-poor approaches, such as Harabagiu and Maiorano (1999), following pioneering work on pronoun resolution by Mitkov (1996Mitkov ( , 1998.…”

Implementation of the rule-based approach for the resolution of strong personal anaphora in Pashto discourse

“…RULES FOR P ASHTO PERSONAL ANAPHORA RESOLUTION There are some rules that help in the process of anaphora resolution, and are usually referred as anaphora resolution factors. Some researchers discussed how these factors play their role in pronominal anaphora resolution [1,2,10,11,14]. The rules that are helpful in the Pashto strong personal anaphora resolution are: animacy, lexical filter, morphological filter, subject and object preferences, section heading and recency [2].…”

“…Several anaphora resolution modules have been implemented [14,6,9,13]. In Urdu language, some work has recently been done on pronominal anaphora resolution [10,11,1] and zero pronouns resolution [12].…”