Abstract | The traditional mention-pair model for coreference resolution cannot capture information beyond mention pairs for both learning and testing. |
Abstract | To deal with this problem, we present an expressive entity-mention model that performs coreference resolution at an entity level. |
Abstract | The evaluation on the ACE data set shows that the ILP based entity-mention model is effective for the coreference resolution task. |
Introduction | Coreference resolution is the process of linking multiple mentions that refer to the same entity. |
Introduction | Most of previous work adopts the mention-pair model, which recasts coreference resolution to a binary classification problem of determining whether or not two mentions in a document are co-referring (e.g. |
Introduction | An alternative learning model that can overcome this problem performs coreference resolution based on entity-mention pairs (Luo et al., 2004; Yang et al., 2004b). |
Related Work | There are plenty of learning-based coreference resolution systems that employ the mention-pair model. |
Related Work | (2004) propose a system that performs coreference resolution by doing search in a large space of entities. |
Related Work | (2004b) suggest an entity-based coreference resolution system. |
Conclusion | A consequence of this research was the creation of It-Bank, a collection of thousands of labelled examples of the pronoun it, which will benefit other coreference resolution researchers. |
Conclusion | Another avenue of study will look at the interaction between coreference resolution and machine translation. |
Evaluation | Standard coreference resolution data sets annotate all noun phrases that have an antecedent noun phrase in the text. |
Introduction | The goal of coreference resolution is to determine which noun phrases in a document refer to the same real-world entity. |
Introduction | As part of this task, coreference resolution systems must decide which pronouns refer to preceding noun phrases (called antecedents) and which do not. |
Introduction | In sentence (1), it is an anaphoric pronoun referring to some previous noun phrase, like “the sauce” or “an appointment.” In sentence (2), it is part of the idiomatic expression “make it” meaning “succeed.” A coreference resolution system should find an antecedent for the first it but not the second. |
Related Work | First of all, research in coreference resolution has shown the benefits of modules for general noun anaphoricity determination (Ng and Cardie, 2002; Denis and Baldridge, 2007). |
Results | Notably, the first noun-phrase before the context is the word “software.” There is strong compatibility between the pronoun-parent “install” and the candidate antecedent “software.” In a full coreference resolution system, when the anaphora resolution module has a strong preference to link it to an antecedent (which it should when the pronoun is indeed referential), we can override a weak non-referential probability. |
Conclusion and Future Work | The aggregation approach described here can be easily extended to improve relation detection and coreference resolution (two argument mentions referring to the same role of related events are likely to corefer). |
Related Work | Almost all the current event extraction systems focus on processing single documents and, except for coreference resolution , operate a sentence at a time (Grishman et al., 2005; Ahn, 2006; Hardy et al., 2006). |
Task and Baseline System | 2 In this paper we don’t consider event mention coreference resolution and so don’t distinguish event mentions and events. |