Joint Anaphoricity Detection and Coreference Resolution with Constrained Latent Structures
نویسندگان
چکیده
This paper introduces a new structured model for learning anaphoricity detection and coreference resolution in a joint fashion. Specifically, we use a latent tree to represent the full coreference and anaphoric structure of a document at a global level, and we jointly learn the parameters of the two models using a version of the structured perceptron algorithm. Our joint structured model is further refined by the use of pairwise constraints which help the model to capture accurately certain patterns of coreference. Our experiments on the CoNLL-2012 English datasets show large improvements in both coreference resolution and anaphoricity detection, compared to various competing architectures. Our best coreference system obtains a CoNLL score of 81.97 on gold mentions, which is to date the best score reported on this setting.
منابع مشابه
Joint Learning for Event Coreference Resolution
While joint models have been developed for many NLP tasks, the vast majority of event coreference resolvers, including the top-performing resolvers competing in the recent TAC KBP 2016 Event Nugget Detection and Coreference task, are pipelinebased, where the propagation of errors from the trigger detection component to the event coreference component is a major performance limiting factor. To a...
متن کاملA Joint Inference Architecture for Global Coreference Clustering with Anaphoricity
We present an architecture for coreference resolution based on joint inference over anaphoricity and coreference, using Markov Logic Networks. Mentions are discriminatively clustered with discourse entities established by an anaphoricity classifier. Our entity-based coreference architecture is realized in a joint inference setting to compensate for erroneous anaphoricity classifications and avo...
متن کاملJoint Determination of Anaphoricity and Coreference Resolution using Integer Programming
Standard pairwise coreference resolution systems are subject to errors resulting from their performing anaphora identification as an implicit part of coreference resolution. In this paper, we propose an integer linear programming (ILP) formulation for coreference resolution which models anaphoricity and coreference as a joint task, such that each local model informs the other for the final assi...
متن کاملDependency-driven Anaphoricity Determination for Coreference Resolution
This paper proposes a dependency-driven scheme to dynamically determine the syntactic parse tree structure for tree kernel-based anaphoricity determination in coreference resolution. Given a full syntactic parse tree, it keeps the nodes and the paths related with current mention based on constituent dependencies from both syntactic and semantic perspectives, while removing the noisy information...
متن کاملGlobal Learning of Noun Phrase Anaphoricity in Coreference Resolution via Label Propagation
Knowledge of noun phrase anaphoricity might be profitably exploited in coreference resolution to bypass the resolution of non-anaphoric noun phrases. However, it is surprising to notice that recent attempts to incorporate automatically acquired anaphoricity information into coreference resolution have been somewhat disappointing. This paper employs a global learning method in determining the an...
متن کامل