Article Structure
Abstract
This paper explores how to apply the notion of caching introduced by Walker (1996) to the task of zero-anaphora resolution.
Introduction
There have been recently increasing concerns with the need for anaphora resolution to make NLP applications such as IE and MT more reliable.
Zero-anaphora resolution
In this paper, we consider only zero-pronouns that function as an obligatory argument of a predicate.
Previous work
Early methods for zero-anaphora resolution were developed with rule-based approaches in mind.
Machine learning-based cache model
As mentioned in Section 2, the procedure for zero-anaphora resolution can be decomposed into two subtasks, namely anaphoricity determination and antecedent identification.
Topics
feature set
- Therefore, the intra-sentential and inter-sentential zero-anaphora resolution models are separately trained by exploiting different feature sets as shown in Table 2.Page 3, “Machine learning-based cache model”
- Table 1: Feature set used in the cache modelsPage 5, “Machine learning-based cache model”
- The feature set used in the cache model is shown in Table l. The ‘CASE_MARKER’ feature roughly captures the salience of the local transition dealt with in Centering Theory, and is also intended to capture the global foci of a text coupled with the BEGINNING feature.Page 5, “Machine learning-based cache model”
- To use the feature set shown in Table 2, morpho-syntactic analysis of a text is performed by the Japanese morpheme analyzer Chasen and the dependency parser CaboCha.Page 5, “Machine learning-based cache model”
See all papers in Proc. ACL 2009 that mention feature set.
See all papers in Proc. ACL that mention feature set.
Back to top.
rule-based
- These methods reach a level comparable to or better than the state-of—the-art rule-based systems (e.g.Page 1, “Introduction”
- On the other hand, rule-based methods derived from theoretical background such as Centering Theory (Grosz et al., 1995) only deal with the salient discourse entities at each point of the discourse status.Page 1, “Introduction”
- Early methods for zero-anaphora resolution were developed with rule-based approaches in mind.Page 2, “Previous work”
- Theory-oriented rule-based methods (Kameyama, 1986; Walker et al., 1994), for example, focus on the Centering Theory (Grosz et al., 1995) and are designed to collect the salient candidate antecedents in the forward-looking center (Cf) list, and then choose the most salient candidate, Cp, as an antecedent of a zero-pronoun according to heuristic rules (e.g.Page 2, “Previous work”
See all papers in Proc. ACL 2009 that mention rule-based.
See all papers in Proc. ACL that mention rule-based.
Back to top.
