Identifying anaphoric and non-anaphoric noun phrases to improve coreference resolution

Ng, Vincent; Cardie, Claire

doi:10.3115/1072228.1072367

Cited by 105 publications

(111 citation statements)

References 17 publications

Supporting

Mentioning

110

Contrasting

Unclassified

Order By: Relevance

“…Cast as an information status task, the goal of discourse-new mention detection is to find discourse referents which were not previously available to the hearer/reader; e.g., see the work of Nissim (2006). Ng and Cardie (2002) develop a discourse-new classifier that targets every kind of NP using a variety of feature types: lexical (string and head matching, conjunction), morpho-syntactic (definiteness, quantification, number), grammatical (appositional or copular context, modifier structure, proper-noun embedding), and shallow semantic (e.g., WordNet features). They incorporate the classifier into their coreference resolution system, pre-filtering NPs that are tagged as discoursenew.…”

Section: Discourse-new Mentionsmentioning

confidence: 99%

Modeling the Lifespan of Discourse Entities with Application to Coreference Resolution

Marneffe

Recasens

Potts

2015

jair

View full text Add to dashboard Cite

A discourse typically involves numerous entities, but few are mentioned more than once. Distinguishing those that die out after just one mention (singleton) from those that lead longer lives (coreferent) would dramatically simplify the hypothesis space for coreference resolution models, leading to increased performance. To realize these gains, we build a classifier for predicting the singleton/coreferent distinction. The model's feature representations synthesize linguistic insights about the factors affecting discourse entity lifespans (especially negation, modality, and attitude predication) with existing results about the benefits of "surface" (part-of-speech and n-gram-based) features for coreference resolution. The model is effective in its own right, and the feature representations help to identify the anchor phrases in bridging anaphora as well. Furthermore, incorporating the model into two very different state-of-the-art coreference resolution systems, one rule-based and the other learning-based, yields significant performance improvements.

show abstract

Section: Discourse-new Mentionsmentioning

confidence: 99%

Modeling the Lifespan of Discourse Entities with Application to Coreference Resolution

Marneffe

Recasens

Potts

2015

jair

View full text Add to dashboard Cite

show abstract

“…A related line of work aims to identify all noun phrases that have an antecedent in text, but these systems typically classify all pronouns as referential and ignore non-referential it [26,11].…”

Section: Related Workmentioning

confidence: 99%

NADA: A Robust System for Non-referential Pronoun Detection

Bergsma

Yarowsky

2011

Anaphora Processing and Applications

View full text Add to dashboard Cite

Abstract. We present Nada: the Non-Anaphoric Detection Algorithm. Nada is a novel, publicly-available program that accurately distinguishes between the referential and non-referential pronoun it in raw English text. Like recent state-of-the-art approaches, Nada uses very large-scale web N-gram features, but Nada makes these features practical by compressing the N-gram counts so they can fit into computer memory. Nada therefore operates as a fast, stand-alone system. Nada also improves over previous web-scale systems by considering the entire sentence, rather than narrow context windows, via long-distance lexical features. Nada very substantially outperforms other state-of-the-art systems in nonreferential detection accuracy.

show abstract

“…Downing [7], Abbott [9] and Heim [10]) and computational linguistics (eg. Vieira et al [11], Ng et al [12] and Fraurud [13]). In this section we will examine verb as well as the adjective inflictions from the perspective or their effect on anaphoric properties.…”

Section: Nps Formed From Normalizationmentioning

confidence: 99%

Generation of Anaphoric Noun Phrases and their coreferential properties

Nand¹,

Yeap²

2010

Proceedings of the Annual International Conference on Advances in Distributed and Parallel Computing ADPC 2010 ADPC 2010

View full text Add to dashboard Cite

Abstract-This paper investigates the generative processes involved in the formation of noun phrases (NPs) from an existing clause in a discourse. A speaker or writer is able to generate a range of NPs from a stated clause to co-refer to the different semantic units of the clause by combining the various primitive components. These generative processes can be grouped into either predicate-deletion or normalization. We use relations defined by Levi [1] as a basis to define constraints used in the formation of NPs by predicate-deletion and empirically determine the conformance level of these constraints with natural discourses. For the normalization process, we argue that the inflicted morpheme's anaphoric properties can be characterized by their suffixes. We also show that, these anaphoric properties are independent of the choice between subjective and objective modifiers. The anaphoric properties of suffix-based morphemes is also empirically investigated for conformance levels, and the results are encouraging.

show abstract

Identifying anaphoric and non-anaphoric noun phrases to improve coreference resolution

Cited by 105 publications

References 17 publications

Modeling the Lifespan of Discourse Entities with Application to Coreference Resolution

Modeling the Lifespan of Discourse Entities with Application to Coreference Resolution

NADA: A Robust System for Non-referential Pronoun Detection

Generation of Anaphoric Noun Phrases and their coreferential properties

Contact Info

Product

Resources

About