Improving Dependency Parsers using Combinatory Categorial Grammar

Ambati, Bharat Ram; Deoskar, Tejaswini; Steedman, Mark

doi:10.3115/v1/e14-4031

Cited by 6 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In future we would like to extract CCG lexicons and/or CCGbanks for the many other languages for which (Buchholz and Marsi 2006;Nivre et al 2007a) and universal dependency treebanks (McDonald et al 2013). 19 State of the art results for parsers trained and tested on the treebank are reported in Ambati et al (2013Ambati et al ( , 2014; Ambati (2016).…”

Section: Resultsmentioning

confidence: 99%

Hindi CCGbank: A CCG treebank from the Hindi dependency treebank

Ambati

Deoskar

Steedman

2017

Lang Resources & Evaluation

Self Cite

View full text Add to dashboard Cite

In this paper, we present an approach for automatically creating a combinatory categorial grammar (CCG) treebank from a dependency treebank for the subject-object-verb language Hindi. Rather than a direct conversion from dependency trees to CCG trees, we propose a two stage approach: a language independent generic algorithm first extracts a CCG lexicon from the dependency treebank. An exhaustive CCG parser then creates a treebank of CCG derivations. We also discuss special cases of this generic algorithm to handle linguistic phenomena specific to Hindi. In doing so we extract different constructions with long-range dependencies like coordinate constructions and non-projective dependencies resulting from constructions like relative clauses, noun elaboration and verbal modifiers.

show abstract

Section: Resultsmentioning

confidence: 99%

Hindi CCGbank: A CCG treebank from the Hindi dependency treebank

Ambati

Deoskar

Steedman

2017

Lang Resources & Evaluation

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this paper, we have shown that supertagging as a method for providing syntactic features for statistical dependency parsing (Ambati et al, 2014;Ouchi et al, 2014) is a form of stacking. Although supertags do not convey as much information as full trees, they improve dependency parsers to an equal amount.…”

Section: Resultsmentioning

confidence: 99%

“…Having fast predictors available for stacking or supertagging suggests an application where speed matters, e.g. Ambati et al (2014) propose supertags to improve the performance of fast parsers in a web scale scenario.…”

Section: Out-of-domain Applicationmentioning

confidence: 99%

See 1 more Smart Citation

Stacking or Supertagging for Dependency Parsing – What’s the Difference?

Faleńska

Björkelund

Çetinoğlu

et al. 2015

Proceedings of the 14th International Conference on Parsing Technologies

View full text Add to dashboard Cite

Supertagging was recently proposed to provide syntactic features for statistical dependency parsing, contrary to its traditional use as a disambiguation step. We conduct a broad range of controlled experiments to compare this specific application of supertagging with another method for providing syntactic features, namely stacking. We find that in this context supertagging is a form of stacking. We furthermore show that (i) a fast parser and a sequence labeler are equally beneficial in supertagging, (ii) supertagging/stacking improve parsing also in a cross-domain setting, and (iii) there are small gains when combining supertagging and stacking, but only if both methods use different tools. The important consideration is therefore not the method but rather the diversity of the tools involved.

show abstract

“…Within dependency parsing, supertags have also been explored in the literature, but prior work mostly treats them as additional features. Ambati et al (2013Ambati et al ( , 2014 use CCG supertags to improve dependency parsing results, while Ouchi et al (2014Ouchi et al ( , 2016 leverage dependency-based supertags as features. Faleńska et al (2015) compare supertagging to parser stacking, where they extract supertags from base parsers to provide additional features for stacked parsers, instead of having a supertagger as a separate component.…”

Section: Case Study On Pp Attachmentmentioning

confidence: 99%

Valency-Augmented Dependency Parsing

Shi

Lee

2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

We present a complete, automated, and efficient approach for utilizing valency analysis in making dependency parsing decisions. It includes extraction of valency patterns, a probabilistic model for tagging these patterns, and a joint decoding process that explicitly considers the number and types of each token's syntactic dependents. On 53 treebanks representing 41 languages in the Universal Dependencies data, we find that incorporating valency information yields higher precision and F1 scores on the core arguments (subjects and complements) and functional relations (e.g., auxiliaries) that we employ for valency analysis. Precision on core arguments improves from 80.87 to 85.43. We further show that our approach can be applied to an ostensibly different formalism and dataset, Tree Adjoining Grammar as extracted from the Penn Treebank; there, we outperform the previous stateof-the-art labeled attachment score by 0.7. Finally, we explore the potential of extending valency patterns beyond their traditional domain by confirming their helpfulness in improving PP attachment decisions. 1

show abstract

Improving Dependency Parsers using Combinatory Categorial Grammar

Cited by 6 publications

References 10 publications

Hindi CCGbank: A CCG treebank from the Hindi dependency treebank

Hindi CCGbank: A CCG treebank from the Hindi dependency treebank

Stacking or Supertagging for Dependency Parsing – What’s the Difference?

Valency-Augmented Dependency Parsing

Contact Info

Product

Resources

About