Translating from morphologically complex languages: A paraphrase-based approach

Preslav Nakov, Hwee Tou Ng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

We propose a novel approach to translating from a morphologically complex language. Unlike previous research, which has targeted word inflections and concatenations, we focus on the pairwise relationship between morphologically related words, which we treat as potential paraphrases and handle using paraphrasing techniques at the word, phrase, and sentence level. An important advantage of this framework is that it can cope with derivational morphology, which has so far remained largely beyond the capabilities of statistical machine translation systems. Our experiments translating from Malay, whose morphology is mostly derivational, into English show significant improvements over rivaling approaches based on five automatic evaluation measures (for 320,000 sentence pairs; 9.5 million English word tokens).

Original languageEnglish
Title of host publicationACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies
Pages1298-1307
Number of pages10
Volume1
Publication statusPublished - 1 Dec 2011
Externally publishedYes
Event49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-HLT 2011 - Portland, OR, United States
Duration: 19 Jun 201124 Jun 2011

Other

Other49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-HLT 2011
CountryUnited States
CityPortland, OR
Period19/6/1124/6/11

Fingerprint

language
experiment
evaluation
Paraphrase
Translating
Complex Language
Derivational Morphology
English Words
Experiment
Statistical Machine Translation
Inflection
Machine Translation System
Paraphrasing
Evaluation

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Nakov, P., & Ng, H. T. (2011). Translating from morphologically complex languages: A paraphrase-based approach. In ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (Vol. 1, pp. 1298-1307)

Translating from morphologically complex languages : A paraphrase-based approach. / Nakov, Preslav; Ng, Hwee Tou.

ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Vol. 1 2011. p. 1298-1307.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nakov, P & Ng, HT 2011, Translating from morphologically complex languages: A paraphrase-based approach. in ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. vol. 1, pp. 1298-1307, 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-HLT 2011, Portland, OR, United States, 19/6/11.
Nakov P, Ng HT. Translating from morphologically complex languages: A paraphrase-based approach. In ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Vol. 1. 2011. p. 1298-1307
Nakov, Preslav ; Ng, Hwee Tou. / Translating from morphologically complex languages : A paraphrase-based approach. ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Vol. 1 2011. pp. 1298-1307
@inproceedings{d4d95752dc34422a903bb6d73f54b31f,
title = "Translating from morphologically complex languages: A paraphrase-based approach",
abstract = "We propose a novel approach to translating from a morphologically complex language. Unlike previous research, which has targeted word inflections and concatenations, we focus on the pairwise relationship between morphologically related words, which we treat as potential paraphrases and handle using paraphrasing techniques at the word, phrase, and sentence level. An important advantage of this framework is that it can cope with derivational morphology, which has so far remained largely beyond the capabilities of statistical machine translation systems. Our experiments translating from Malay, whose morphology is mostly derivational, into English show significant improvements over rivaling approaches based on five automatic evaluation measures (for 320,000 sentence pairs; 9.5 million English word tokens).",
author = "Preslav Nakov and Ng, {Hwee Tou}",
year = "2011",
month = "12",
day = "1",
language = "English",
isbn = "9781932432879",
volume = "1",
pages = "1298--1307",
booktitle = "ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies",

}

TY - GEN

T1 - Translating from morphologically complex languages

T2 - A paraphrase-based approach

AU - Nakov, Preslav

AU - Ng, Hwee Tou

PY - 2011/12/1

Y1 - 2011/12/1

N2 - We propose a novel approach to translating from a morphologically complex language. Unlike previous research, which has targeted word inflections and concatenations, we focus on the pairwise relationship between morphologically related words, which we treat as potential paraphrases and handle using paraphrasing techniques at the word, phrase, and sentence level. An important advantage of this framework is that it can cope with derivational morphology, which has so far remained largely beyond the capabilities of statistical machine translation systems. Our experiments translating from Malay, whose morphology is mostly derivational, into English show significant improvements over rivaling approaches based on five automatic evaluation measures (for 320,000 sentence pairs; 9.5 million English word tokens).

AB - We propose a novel approach to translating from a morphologically complex language. Unlike previous research, which has targeted word inflections and concatenations, we focus on the pairwise relationship between morphologically related words, which we treat as potential paraphrases and handle using paraphrasing techniques at the word, phrase, and sentence level. An important advantage of this framework is that it can cope with derivational morphology, which has so far remained largely beyond the capabilities of statistical machine translation systems. Our experiments translating from Malay, whose morphology is mostly derivational, into English show significant improvements over rivaling approaches based on five automatic evaluation measures (for 320,000 sentence pairs; 9.5 million English word tokens).

UR - http://www.scopus.com/inward/record.url?scp=84859045137&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859045137&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84859045137

SN - 9781932432879

VL - 1

SP - 1298

EP - 1307

BT - ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies

ER -