Joint part-of-speech and dependency projection from multiple sources

Anders Trærup Johannsen; Zeljko Agic; Anders Søgaard

Joint part-of-speech and dependency projection from multiple sources

Anders Trærup Johannsen, Zeljko Agic, Anders Søgaard

Department of Nordic Studies and Linguistics

3 Citations (Scopus)

Abstract

Most previous work on annotation projection has been limited to a subset of Indo-European languages, using only a single source language, and projecting annotation for one task at a time. In contrast, we present an Integer Linear Programming (ILP) algorithm that simultaneously projects annotation for multiple tasks from multiple source languages, relying on parallel corpora available for hundreds of languages. When training POS taggers and dependency parsers on jointly projected POS tags and syntactic dependencies using our algorithm, we obtain better performance than a standard approach on 20/23 languages using one parallel corpus; and 18/27 languages using another.

Original language	English
Title of host publication	Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics
Volume	2 (Short papers)
Publisher	Association for Computational Linguistics
Publication date	2016
ISBN (Print)	978-1-945626-01-2
Publication status	Published - 2016
Event	54th Annual Meeting of the Association for Computational Linguistics - Berlin, Germany Duration: 7 Aug 2016 → 12 Aug 2016 Conference number: 54

Conference

Conference	54th Annual Meeting of the Association for Computational Linguistics
Number	54
Country/Territory	Germany
City	Berlin
Period	07/08/2016 → 12/08/2016

Access to Document

https://www.aclweb.org/anthology/P/P16/P16-2091.pdf

Cite this

Joint part-of-speech and dependency projection from multiple sources. / Johannsen, Anders Trærup; Agic, Zeljko; Søgaard, Anders.

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Vol. 2 (Short papers) Association for Computational Linguistics, 2016.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Johannsen, AT, Agic, Z & Søgaard, A 2016, Joint part-of-speech and dependency projection from multiple sources. in Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. vol. 2 (Short papers), Association for Computational Linguistics, 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Germany, 07/08/2016. <https://www.aclweb.org/anthology/P/P16/P16-2091.pdf>

@inproceedings{b6018fa66dbb46098699d5e0a14f3cb9,

title = "Joint part-of-speech and dependency projection from multiple sources",

abstract = "Most previous work on annotation projection has been limited to a subset of Indo-European languages, using only a single source language, and projecting annotation for one task at a time. In contrast, we present an Integer Linear Programming (ILP) algorithm that simultaneously projects annotation for multiple tasks from multiple source languages, relying on parallel corpora available for hundreds of languages. When training POS taggers and dependency parsers on jointly projected POS tags and syntactic dependencies using our algorithm, we obtain better performance than a standard approach on 20/23 languages using one parallel corpus; and 18/27 languages using another.",

author = "Johannsen, {Anders Tr{\ae}rup} and Zeljko Agic and Anders S{\o}gaard",

year = "2016",

language = "English",

isbn = " 978-1-945626-01-2",

volume = "2 (Short papers)",

booktitle = "Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics",

note = "54th Annual Meeting of the Association for Computational Linguistics ; Conference date: 07-08-2016 Through 12-08-2016",

}

TY - GEN

T1 - Joint part-of-speech and dependency projection from multiple sources

AU - Johannsen, Anders Trærup

AU - Agic, Zeljko

AU - Søgaard, Anders

N1 - Conference code: 54

PY - 2016

Y1 - 2016

N2 - Most previous work on annotation projection has been limited to a subset of Indo-European languages, using only a single source language, and projecting annotation for one task at a time. In contrast, we present an Integer Linear Programming (ILP) algorithm that simultaneously projects annotation for multiple tasks from multiple source languages, relying on parallel corpora available for hundreds of languages. When training POS taggers and dependency parsers on jointly projected POS tags and syntactic dependencies using our algorithm, we obtain better performance than a standard approach on 20/23 languages using one parallel corpus; and 18/27 languages using another.

AB - Most previous work on annotation projection has been limited to a subset of Indo-European languages, using only a single source language, and projecting annotation for one task at a time. In contrast, we present an Integer Linear Programming (ILP) algorithm that simultaneously projects annotation for multiple tasks from multiple source languages, relying on parallel corpora available for hundreds of languages. When training POS taggers and dependency parsers on jointly projected POS tags and syntactic dependencies using our algorithm, we obtain better performance than a standard approach on 20/23 languages using one parallel corpus; and 18/27 languages using another.

M3 - Article in proceedings

SN - 978-1-945626-01-2

VL - 2 (Short papers)

BT - Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics

PB - Association for Computational Linguistics

T2 - 54th Annual Meeting of the Association for Computational Linguistics

Y2 - 7 August 2016 through 12 August 2016

ER -

Joint part-of-speech and dependency projection from multiple sources

Abstract

Conference

Access to Document

Fingerprint

Cite this