German and French Neural Supertagging Experiments for LTAG Parsing

Tatiana Bladier; Andreas van Cranenburgh; Younes Samih; Laura Kallmeyer

German and French Neural Supertagging Experiments for LTAG Parsing

Tatiana Bladier, Andreas van Cranenburgh, Younes Samih, Laura Kallmeyer

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

3 Citations (Scopus)

182 Downloads (Pure)

Abstract

We present ongoing work on data-driven parsing of German and French with Lexicalized Tree Adjoining Grammars. We use a supertagging approach combined with deep learning. We show the challenges of extracting LTAG supertags from the
French Treebank, introduce the use of leftand right-sister-adjunction, present a neural architecture for the supertagger, and report experiments of n-best supertagging for French and German.

Original language	English
Title of host publication	Proceedings of ACL 2018, Student Research Workshop
Editors	Vered Shwartz, Jeniya Tabassum, Rob Voigt, Wanxiang Che, Marie-Catherine de Marneffe, Malvina Nissim
Place of Publication	Melbourne
Publisher	Association for Computational Linguistics (ACL)
Number of pages	8
Publication status	Published - Jul-2018
Externally published	Yes

Access to Document

German and French Neural Supertagging Experiments for LTAG ParsingFinal publisher's version, 660 KBLicence: Unspecified

Handle.net

Persistent link

Cite this

Bladier, Tatiana ; van Cranenburgh, Andreas ; Samih, Younes et al. / German and French Neural Supertagging Experiments for LTAG Parsing. Proceedings of ACL 2018, Student Research Workshop. editor / Vered Shwartz ; Jeniya Tabassum ; Rob Voigt ; Wanxiang Che ; Marie-Catherine de Marneffe ; Malvina Nissim . Melbourne : Association for Computational Linguistics (ACL), 2018.

@inproceedings{68782131224b4dab8688cacfafefb3b7,

title = "German and French Neural Supertagging Experiments for LTAG Parsing",

abstract = "We present ongoing work on data-driven parsing of German and French with Lexicalized Tree Adjoining Grammars. We use a supertagging approach combined with deep learning. We show the challenges of extracting LTAG supertags from theFrench Treebank, introduce the use of leftand right-sister-adjunction, present a neural architecture for the supertagger, and report experiments of n-best supertagging for French and German.",

author = "Tatiana Bladier and {van Cranenburgh}, Andreas and Younes Samih and Laura Kallmeyer",

year = "2018",

month = jul,

language = "English",

editor = "Shwartz, {Vered } and Tabassum, {Jeniya } and Voigt, {Rob } and Che, {Wanxiang } and {de Marneffe}, {Marie-Catherine } and {Nissim }, {Malvina }",

booktitle = "Proceedings of ACL 2018, Student Research Workshop",

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

}

German and French Neural Supertagging Experiments for LTAG Parsing. / Bladier, Tatiana; van Cranenburgh, Andreas; Samih, Younes et al.
Proceedings of ACL 2018, Student Research Workshop. ed. / Vered Shwartz; Jeniya Tabassum; Rob Voigt; Wanxiang Che; Marie-Catherine de Marneffe; Malvina Nissim . Melbourne: Association for Computational Linguistics (ACL), 2018.

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

TY - GEN

T1 - German and French Neural Supertagging Experiments for LTAG Parsing

AU - Bladier, Tatiana

AU - van Cranenburgh, Andreas

AU - Samih, Younes

AU - Kallmeyer, Laura

PY - 2018/7

Y1 - 2018/7

N2 - We present ongoing work on data-driven parsing of German and French with Lexicalized Tree Adjoining Grammars. We use a supertagging approach combined with deep learning. We show the challenges of extracting LTAG supertags from theFrench Treebank, introduce the use of leftand right-sister-adjunction, present a neural architecture for the supertagger, and report experiments of n-best supertagging for French and German.

AB - We present ongoing work on data-driven parsing of German and French with Lexicalized Tree Adjoining Grammars. We use a supertagging approach combined with deep learning. We show the challenges of extracting LTAG supertags from theFrench Treebank, introduce the use of leftand right-sister-adjunction, present a neural architecture for the supertagger, and report experiments of n-best supertagging for French and German.

M3 - Conference contribution

BT - Proceedings of ACL 2018, Student Research Workshop

A2 - Shwartz, Vered

A2 - Tabassum, Jeniya

A2 - Voigt, Rob

A2 - Che, Wanxiang

A2 - de Marneffe, Marie-Catherine

A2 - Nissim , Malvina

PB - Association for Computational Linguistics (ACL)

CY - Melbourne

ER -

German and French Neural Supertagging Experiments for LTAG Parsing

Abstract

Access to Document

Handle.net

Fingerprint

Cite this