Discontinuous Data-Oriented Parsing: A mildly context-sensitive all-fragments grammar

Andreas van Cranenburgh; Remko Scha; Federico Sangati

Discontinuous Data-Oriented Parsing: A mildly context-sensitive all-fragments grammar

Andreas van Cranenburgh, Remko Scha, Federico Sangati

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

6 Citations (Scopus)

154 Downloads (Pure)

Abstract

Recent advances in parsing technology have made treebank parsing with discontinuous constituents possible, with parser output of competitive quality (Kallmeyer and Maier, 2010). We apply Data-Oriented Parsing (DOP) to a grammar formalism that allows for discontinuous trees (LCFRS). Decisions during parsing are conditioned on all possible fragments, resulting in improved performance.
Despite the fact that both DOP and discontinuity present formidable challenges in terms of computational complexity, the model is reasonably efficient, and surpasses the state of the art in discontinuous parsing.

Original language	English
Title of host publication	oceedings of the Second Workshop on Statistical Parsing of Morphologically Rich Languages
Place of Publication	Dublin, Ireland
Publisher	Association for Computational Linguistics (ACL)
Pages	34-44
Number of pages	11
Publication status	Published - Oct-2011
Externally published	Yes

Access to Document

Discontinuous Data-Oriented Parsing: A mildly context-sensitive all-fragments grammarFinal publisher's version, 298 KBLicence: CC BY-NC-SA

http://aclweb.org/anthology/W11-3805Licence: CC BY-NC-SA

Handle.net

Persistent link

Cite this

@inproceedings{14526bbe7a9c4c32bbaae74051b8f247,

title = "Discontinuous Data-Oriented Parsing: A mildly context-sensitive all-fragments grammar",

abstract = "Recent advances in parsing technology have made treebank parsing with discontinuous constituents possible, with parser output of competitive quality (Kallmeyer and Maier, 2010). We apply Data-Oriented Parsing (DOP) to a grammar formalism that allows for discontinuous trees (LCFRS). Decisions during parsing are conditioned on all possible fragments, resulting in improved performance.Despite the fact that both DOP and discontinuity present formidable challenges in terms of computational complexity, the model is reasonably efficient, and surpasses the state of the art in discontinuous parsing.",

author = "{van Cranenburgh}, Andreas and Remko Scha and Federico Sangati",

year = "2011",

month = oct,

language = "English",

pages = "34--44",

booktitle = "oceedings of the Second Workshop on Statistical Parsing of Morphologically Rich Languages",

publisher = "Association for Computational Linguistics (ACL)",

}

Discontinuous Data-Oriented Parsing: A mildly context-sensitive all-fragments grammar. / van Cranenburgh, Andreas; Scha, Remko; Sangati, Federico.
oceedings of the Second Workshop on Statistical Parsing of Morphologically Rich Languages. Dublin, Ireland: Association for Computational Linguistics (ACL), 2011. p. 34-44.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Discontinuous Data-Oriented Parsing

T2 - A mildly context-sensitive all-fragments grammar

AU - van Cranenburgh, Andreas

AU - Scha, Remko

AU - Sangati, Federico

PY - 2011/10

Y1 - 2011/10

N2 - Recent advances in parsing technology have made treebank parsing with discontinuous constituents possible, with parser output of competitive quality (Kallmeyer and Maier, 2010). We apply Data-Oriented Parsing (DOP) to a grammar formalism that allows for discontinuous trees (LCFRS). Decisions during parsing are conditioned on all possible fragments, resulting in improved performance.Despite the fact that both DOP and discontinuity present formidable challenges in terms of computational complexity, the model is reasonably efficient, and surpasses the state of the art in discontinuous parsing.

AB - Recent advances in parsing technology have made treebank parsing with discontinuous constituents possible, with parser output of competitive quality (Kallmeyer and Maier, 2010). We apply Data-Oriented Parsing (DOP) to a grammar formalism that allows for discontinuous trees (LCFRS). Decisions during parsing are conditioned on all possible fragments, resulting in improved performance.Despite the fact that both DOP and discontinuity present formidable challenges in terms of computational complexity, the model is reasonably efficient, and surpasses the state of the art in discontinuous parsing.

M3 - Conference contribution

SP - 34

EP - 44

BT - oceedings of the Second Workshop on Statistical Parsing of Morphologically Rich Languages

PB - Association for Computational Linguistics (ACL)

CY - Dublin, Ireland

ER -

Discontinuous Data-Oriented Parsing: A mildly context-sensitive all-fragments grammar

Abstract

Access to Document

Handle.net

Fingerprint

Cite this