Coreference Resolution Using Verbs Knowledge

Coreference resolution is the problem of clustering mentions in a text that refer to the same entities, and is a crucial and difficult step in every natural language processing task. Despite the efforts that have been made to solve this problem during the past, its performance still does not meet today’s application requirements. Given the importance of the verbs in sentences, in this work, we tried to incorporate three types of their information on coreference resolution problem, namely, selectional restriction of verbs on their arguments, semantic relation between verb pairs, and the truth that arguments of a verb cannot be coreferent of each other. As a needed resource for supporting our model, we generate a repository of semantic relations between verb pairs automatically using Distributional Memory (DM), a state-of-the-art framework for distributional semantics. This resource consists of pairs of verbs associated with their probable arguments, their role mapping, and significance scores based on our measures. Our proposed model for coreference resolution encodes verb’s knowledge with Markov logic network rules on top of the deterministic Stanford coreference resolution system. Experiment results show that this semantic layer can improve the recall of the Stanford system while preserves its precision and improves it slightly.

Keywords:

Coreference resolution , anaphora resolution , semantically related verbs , text inference , NLP