Corpus-Oriented Grammar Development for Acquiring a Head-Driven Phrase Structure Grammar from the Penn Treebank

Miyao, Yusuke; Ninomiya, Takashi; Tsujii, Jun’ichi

doi:10.1007/978-3-540-30211-7_72

Cited by 67 publications

(70 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method is also applicable to other deep dependency structures, e.g. HPSG predicate-argument analysis (Miyao et al, 2004), as well as other graphstructured semantic representations, e.g. Abstract Meaning Representations (Banarescu et al, 2013).…”

Section: Resultsmentioning

confidence: 99%

“…Besides CCG, similar deep dependency structures can be also extracted from parsers under other deep grammar formalisms, e.g. LFG (King et al, 2003) and HPSG (Miyao et al, 2004).…”

Section: Related Workmentioning

confidence: 99%

“…Our algorithm is also applicable to other graphstructured representations, e.g. HPSG predicateargument analysis (Miyao et al, 2004). Hockenmaier and Steedman (2007) developed linguistic resources, namely CCGBank, from the Penn Treebank (PTB; Marcus et al, 1993).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Data-Driven, Factorization Parser for CCG Dependency Structures

Sun

Wan

2015

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

View full text Add to dashboard Cite

This paper is concerned with building CCG-grounded, semantics-oriented deep dependency structures with a data-driven, factorization model. Three types of factorization together with different higherorder features are designed to capture different syntacto-semantic properties of functor-argument dependencies. Integrating heterogeneous factorizations results in intractability in decoding. We propose a principled method to obtain optimal graphs based on dual decomposition. Our parser obtains an unlabeled f-score of 93.23 on the CCGBank data, resulting in an error reduction of 6.5% over the best published result. which yields a significant improvement over the best published result in the literature. Our implementation is available at http://www.icst. pku.edu.cn/lcwm/grass.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Besides CCG, similar deep dependency structures can be also extracted from parsers under other deep grammar formalisms, e.g. LFG (King et al, 2003) and HPSG (Miyao et al, 2004).…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Data-Driven, Factorization Parser for CCG Dependency Structures

Sun

Wan

2015

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

View full text Add to dashboard Cite

show abstract

“…DM is derived from LinGO English Resource Grammar (ERG) annotations in DeepBank (Flickinger et al, 2012). PAS is derived from the Enju HPSG treebank using the conversion rules of Miyao et al (2004). PCEDT is derived from the tectogrammatical layer of the Prague Czech-English Dependency Treebank (Hajič, 1998).…”

Section: Formalismsmentioning

confidence: 99%

CMU: Arc-Factored, Discriminative Semantic Dependency Parsing

Thomson

O’Connor

Flanigan

et al. 2014

Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014)

View full text Add to dashboard Cite

show abstract

“…Accordingly resource problems can be exacerbated in multilingual grammar development scenarios, particularly across typologically different languages. 1 Recently a number of researchers have addressed the knowledge acquisition problem in broad-coverage, deep, unification grammar development for English: Miyao et al (2003Miyao et al ( , 2004 show how HPSG resources and Cahill et al (2002Cahill et al ( , 2004 and O'Donovan et al (2004) show how LFG resources can be induced from the Penn-II Treebank. Hockenmaier and Steedman (2002) and Hockenmaier (2003) show how combinatory categorial grammatical resources can be induced.…”

Section: Introductionmentioning

confidence: 99%

Treebank-Based Acquisition of Multilingual Unification Grammar Resources

Cahill

Burke

Forst³

et al. 2005

Res Lang Comput

View full text Add to dashboard Cite

Abstract. Deep unification-(constraint-)based grammars are usually hand-crafted. Scaling such grammars from fragments to unrestricted text is time-consuming and expensive. This problem can be exacerbated in multilingual broad-coverage grammar development scenarios. Cahill et al. (2002Cahill et al. ( , 2004 and O'Donovan et al. (2004) present an automatic f-structure annotation-based methodology to acquire broad-coverage, deep, Lexical-Functional Grammar (LFG) resources for English from the Penn-II Treebank. In this paper we show how this model can be adapted to a multilingual grammar development scenario to induce robust, wide-coverage, PCFG-based LFG approximations for German from the TIGER Treebank. We show how the architecture of LFG, in particular the distinction between c-structure and f-structure representations, facilitates multilingual, treebank-based unification grammar induction, allowing us to cross-linguistically reuse the lexical extraction and parsing modules from O' Donovan et al. (2004) and Cahill et al. (2004), respectively. We evaluate our grammars against the PARC 700 Dependency Bank , against dependency structures for 2000 held-out sentences from the TIGER Corpus as well as against a hand-crafted dependency gold standard for 100 TIGER trees. Currently, our resources achieve 81.79% f-score against the PARC 700, a 2.19% improvement over the best result reported for a hand-crafted grammar in Kaplan et al. (2004), 74.6% against the 2000 held-out TIGER dependency structures and 71.08% against the 100-sentence TIGER gold standard, with substantially improved coverage compared to hand-crafted resources. We have since applied our methodology to induce wide-coverage LFG resources for Chinese (Burke et al., 2004b) from the Penn Chinese Treebank (Xue et al., 2002) and for Spanish from the CAST3LB Treebank (Civit, 2003).

show abstract

Corpus-Oriented Grammar Development for Acquiring a Head-Driven Phrase Structure Grammar from the Penn Treebank

Cited by 67 publications

References 9 publications

A Data-Driven, Factorization Parser for CCG Dependency Structures

A Data-Driven, Factorization Parser for CCG Dependency Structures

CMU: Arc-Factored, Discriminative Semantic Dependency Parsing

Treebank-Based Acquisition of Multilingual Unification Grammar Resources

Contact Info

Product

Resources

About