Coordination Annotation Extension in the Penn Tree Bank

Ficler, Jessica; Goldberg, Yoav

doi:10.18653/v1/p16-1079

Cited by 20 publications

(16 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We evaluate our models on their ability to identify conjunction boundaries in the extended Penn Treebank (Ficler and Goldberg, 2016) and Genia Treebank (Ohta et al, 2002) Berkeley parser (Petrov et al, 2006) and the discriminative Zpar parser (Zhang and Clark, 2011). When evaluating on the Genia treebank, we compare to the results of the discriminative coordination-prediction model of Hara et al (2009).…”

Section: Methodsmentioning

confidence: 99%

“…However, using the Genia corpus is not ideal since it is in a specialized domain and much smaller than the PTB. In this work we rely on a version of the PTB released by Ficler and Goldberg (2016) in which the above deficiencies are manually resolved. In particular, coordinating elements, coordination phrases and conjunct boundaries are explicitly marked with specialized function labels.…”

Section: Coordination In the Ptbmentioning

confidence: 99%

See 1 more Smart Citation

A Neural Network for Coordination Boundary Prediction

Ficler

Goldberg

2016

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

Self Cite

View full text Add to dashboard Cite

We propose a neural-network based model for coordination boundary prediction. The network is designed to incorporate two signals: the similarity between conjuncts and the observation that replacing the whole coordination phrase with a conjunct tends to produce a coherent sentences. The modeling makes use of several LSTM networks. The model is trained solely on conjunction annotations in a Treebank, without using external resources. We show improvements on predicting coordination boundaries on the PTB compared to two state-of-the-art parsers; as well as improvement over previous coordination boundary prediction systems on the Genia corpus.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Coordination In the Ptbmentioning

confidence: 99%

A Neural Network for Coordination Boundary Prediction

Ficler

Goldberg

2016

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…NomBank (Meyers et al, 2004) extended the argument structure for instances of common nouns. Vadas and Curran (2007), and Ficler and Goldberg (2016) extended the PTB with noun phrase and coordination annotations, respectively.…”

Section: Related Workmentioning

confidence: 99%

NNE: A Dataset for Nested Named Entity Recognition in English Newswire

Ringland¹,

Dai²,

Hachey³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Named entity recognition (NER) is widely used in natural language processing applications and downstream tasks. However, most NER tools target flat annotation from popular datasets, eschewing the semantic information available in nested entity mentions. We describe NNE-a fine-grained, nested named entity dataset over the full Wall Street Journal portion of the Penn Treebank (PTB). Our annotation comprises 279,795 mentions of 114 entity types with up to 6 layers of nesting. We hope the public release of this large dataset for English newswire will encourage development of new techniques for nested NER.

show abstract

“…We trained two additional RNNG models on 38,546 sentences from the Penn Treebank annotated with two different schemes: The first, RNNG (PTB-control) was trained with the original Penn Treebank annotation. The second, RNNG (PTB-coord), was trained on the same sentences, but with an extended coordination annotation scheme, meant to employ the scheme employed in the FTB, adapted from Ficler and Goldberg (2016). We stripped empty categories from their scheme and only kept the NP-COORD label for constituents inside a coordination structure.…”

Section: A the Effect Of Annotation Schemesmentioning

confidence: 99%

Representation of Constituents in Neural Language Models: Coordination Phrase as a Case Study

An¹,

Qian

Wilcox

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Neural language models have achieved stateof-the-art performances on many NLP tasks, and recently have been shown to learn a number of hierarchically-sensitive syntactic dependencies between individual words. However, equally important for language processing is the ability to combine words into phrasal constituents, and use constituent-level features to drive downstream expectations. Here we investigate neural models' ability to represent constituent-level features, using coordinated noun phrases as a case study. We assess whether different neural language models trained on English and French represent phrase-level number and gender features, and use those features to drive downstream expectations. Our results suggest that models use a linear combination of NP constituent number to drive CoordNP/verb number agreement. This behavior is highly regular and even sensitive to local syntactic context, however it differs crucially from observed human behavior. Models have less success with gender agreement. Models trained on large corpora perform best, and there is no obvious advantage for models trained using explicit syntactic supervision.

show abstract

Coordination Annotation Extension in the Penn Tree Bank

Cited by 20 publications

References 7 publications

A Neural Network for Coordination Boundary Prediction

A Neural Network for Coordination Boundary Prediction

NNE: A Dataset for Nested Named Entity Recognition in English Newswire

Representation of Constituents in Neural Language Models: Coordination Phrase as a Case Study

Contact Info

Product

Resources

About