An integrated model for anaphora resolution
Ruslan Mitkov · 1994
The paper discusses a new knowledge-based and sublanguage-oriented model for anaphora resolution, which integrates syntactic, semantic, discourse, domain and heuristical knowledge for the sublanguage of computer science. Special attention is paid to a new approach for tracking the center throughout a discourse segment, which plays an important role in proposing the most likely antecedent to the anaphor in case of ambiguity.