A mention-synchronous coreference resolution algorithm based on the Bell tree

Luo, Xiaoqiang; Ittycheriah, Abraham; Jing, He; Kambhatla, Nanda; Roukos, Salim

doi:10.3115/1218955.1218973

Cited by 128 publications

(126 citation statements)

References 12 publications

Supporting

Mentioning

125

Contrasting

Order By: Relevance

“…They should not be allowed to corefer with other NPs. Consequently, the use we make of nominal-predicate and appositive features is the opposite to that made by systems trained on the MUC or ACE corpora [4,13]. Besides, the fact that AnCora contains gold standard annotation from the morphological to the semantic levels makes it possible to include additional features that rely on such rich information.…”

Section: Pairwise Comparison Featuresmentioning

confidence: 99%

See 1 more Smart Citation

A Deeper Look into Features for Coreference Resolution

Recasens

Hovy

2009

Anaphora Processing and Applications

View full text Add to dashboard Cite

Abstract. All automated coreference resolution systems consider a number of features, such as head noun, NP type, gender, or number. Athough the particular features used is one of the key factors for determining performance, they have not received much attention, especially for languages other than English. This paper delves into a considerable number of pairwise comparison features for coreference, including old and novel features, with a special focus on the Spanish language. We consider the contribution of each of the features as well as the interaction between them. In addition, given the problem of class imbalance in coreference resolution, we analyze the effect of sample selection. From the experiments with TiMBL (Tilburg Memory-Based Learner) on the AnCora corpus, interesting conclusions are drawn from both a linguistic and a computational perspective.

show abstract

Section: Pairwise Comparison Featuresmentioning

confidence: 99%

“…The features that have been shown to obtain better results in previous works [4,5,13] capture the most basic information on which coreference depends, but form a reduced feature set that does not account for all kinds of coreference relations.…”

Section: Pairwise Comparison Featuresmentioning

confidence: 99%

A Deeper Look into Features for Coreference Resolution

Recasens

Hovy

2009

Anaphora Processing and Applications

View full text Add to dashboard Cite

show abstract

“…Several works have explored using non-local entity-level features in mention-entity models that assign a single mention to a (partially completed) cluster (Luo et al, 2004;Yang et al, 2008;Rahman and Ng, 2011). Our system, however, builds clusters incrementally through merge operations, and so can operate in an easy-first fashion.…”

Section: Related Workmentioning

confidence: 99%

Entity-Centric Coreference Resolution with Model Stacking

Clark

Manning

2015

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Confere

140

155

View full text Add to dashboard Cite

Mention pair models that predict whether or not two mentions are coreferent have historically been very effective for coreference resolution, but do not make use of entity-level information. However, we show that the scores produced by such models can be aggregated to define powerful entity-level features between clusters of mentions. Using these features, we train an entity-centric coreference system that learns an effective policy for building up coreference chains incrementally. The mention pair scores are also used to prune the search space the system works in, allowing for efficient training with an exact loss function. We evaluate our system on the English portion of the 2012 CoNLL Shared Task dataset and show that it improves over the current state of the art.

show abstract

“…The annotation guidelines, corpora, and other resources in support of the ACE program are available through LDC. The ACE data has been used in a number of experiments on coreference resolution, both data-driven and knowledge-based (see e.g., (Luo et al, 2004), (Chen and Hacioglu, 2006), (Ng, 2007), and (Haghighi and Klein, 2009)). …”

Section: Corpora Annotated With Coreferencementioning

confidence: 99%

SUC-CORE: A Balanced Corpus Annotated with Noun Phrase Coreference

Björkenstam

2013

NEJLT

View full text Add to dashboard Cite

This paper describes SUC-CORE, a subset of the Stockholm Umeå Corpus and the Swedish Treebank annotated with noun phrase coreference. While most coreference annotated corpora consist of texts of similar types within related domains, SUC-CORE consists of both informative and imaginative prose and covers a wide range of literary genres and domains. This allows for exploration of coreference across different text types, but it also means that there are limited amounts of data within each type. Future work on coreference resolution for Swedish should include making more annotated data available for the research community.

show abstract

A mention-synchronous coreference resolution algorithm based on the Bell tree

Cited by 128 publications

References 12 publications

A Deeper Look into Features for Coreference Resolution

A Deeper Look into Features for Coreference Resolution

Entity-Centric Coreference Resolution with Model Stacking

SUC-CORE: A Balanced Corpus Annotated with Noun Phrase Coreference

Contact Info

Product

Resources

About