Using discourse structure improves machine translation evaluation

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

23 Citations (Scopus)

Abstract

We present experiments in using discourse structure for improving machine translation evaluation. We first design two discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordance with the Rhetorical Structure Theory. Then, we show that these measures can help improve a number of existing machine translation evaluation metrics both at the segment- and at the system-level. Rather than proposing a single new metric, we show that discourse information is complementary to the state-of-the-art evaluation metrics, and thus should be taken into account in the development of future richer evaluation metrics.

Original languageEnglish
Title of host publication52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages687-698
Number of pages12
Volume1
ISBN (Print)9781937284725
Publication statusPublished - 1 Jan 2014
Event52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Baltimore, MD, United States
Duration: 22 Jun 201427 Jun 2014

Other

Other52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014
CountryUnited States
CityBaltimore, MD
Period22/6/1427/6/14

Fingerprint

discourse
evaluation
Evaluation
Discourse Structure
Machine Translation
experiment
Discourse
Kernel
Rhetorical Structure Theory
Experiment

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Guzmán, F., Rayhan Joty, S., Marques, L., & Nakov, P. (2014). Using discourse structure improves machine translation evaluation. In 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings of the Conference (Vol. 1, pp. 687-698). Association for Computational Linguistics (ACL).

Using discourse structure improves machine translation evaluation. / Guzmán, Francisco; Rayhan Joty, Shafiq; Marques, Lluis; Nakov, Preslav.

52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings of the Conference. Vol. 1 Association for Computational Linguistics (ACL), 2014. p. 687-698.

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

Guzmán, F, Rayhan Joty, S, Marques, L & Nakov, P 2014, Using discourse structure improves machine translation evaluation. in 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings of the Conference. vol. 1, Association for Computational Linguistics (ACL), pp. 687-698, 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014, Baltimore, MD, United States, 22/6/14.
Guzmán F, Rayhan Joty S, Marques L, Nakov P. Using discourse structure improves machine translation evaluation. In 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings of the Conference. Vol. 1. Association for Computational Linguistics (ACL). 2014. p. 687-698
Guzmán, Francisco ; Rayhan Joty, Shafiq ; Marques, Lluis ; Nakov, Preslav. / Using discourse structure improves machine translation evaluation. 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings of the Conference. Vol. 1 Association for Computational Linguistics (ACL), 2014. pp. 687-698
@inproceedings{9c0c5cc1416746adb37379e7b0410323,
title = "Using discourse structure improves machine translation evaluation",
abstract = "We present experiments in using discourse structure for improving machine translation evaluation. We first design two discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordance with the Rhetorical Structure Theory. Then, we show that these measures can help improve a number of existing machine translation evaluation metrics both at the segment- and at the system-level. Rather than proposing a single new metric, we show that discourse information is complementary to the state-of-the-art evaluation metrics, and thus should be taken into account in the development of future richer evaluation metrics.",
author = "Francisco Guzm{\'a}n and {Rayhan Joty}, Shafiq and Lluis Marques and Preslav Nakov",
year = "2014",
month = "1",
day = "1",
language = "English",
isbn = "9781937284725",
volume = "1",
pages = "687--698",
booktitle = "52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Using discourse structure improves machine translation evaluation

AU - Guzmán, Francisco

AU - Rayhan Joty, Shafiq

AU - Marques, Lluis

AU - Nakov, Preslav

PY - 2014/1/1

Y1 - 2014/1/1

N2 - We present experiments in using discourse structure for improving machine translation evaluation. We first design two discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordance with the Rhetorical Structure Theory. Then, we show that these measures can help improve a number of existing machine translation evaluation metrics both at the segment- and at the system-level. Rather than proposing a single new metric, we show that discourse information is complementary to the state-of-the-art evaluation metrics, and thus should be taken into account in the development of future richer evaluation metrics.

AB - We present experiments in using discourse structure for improving machine translation evaluation. We first design two discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordance with the Rhetorical Structure Theory. Then, we show that these measures can help improve a number of existing machine translation evaluation metrics both at the segment- and at the system-level. Rather than proposing a single new metric, we show that discourse information is complementary to the state-of-the-art evaluation metrics, and thus should be taken into account in the development of future richer evaluation metrics.

UR - http://www.scopus.com/inward/record.url?scp=84906925055&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906925055&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781937284725

VL - 1

SP - 687

EP - 698

BT - 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

ER -