Multilingual Robust Anaphora Resolution

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. This approach is a modification of the practical approach (Mitkov 1998a) and operates on texts pre-processed by a partof-speech tagger. Input is checked against agreement and a number of antecedent indicators. Candidates are assigned scores by each indicator and the candidate with the highest aggregate score is returned as the antecedent. We propose this approach as a platform for multilingual pronoun resolution. The robust approach was initially developed and tested for English, but we have also adapted and tested it for Polish and Arabic. For both languages, we found that adaptation required minimum modification and that further, even if used unmodified, the approach delivers acceptable success rates. Preliminary evaluation reports high success rates in the range of and over 90%