The UPC TweetMT participation: Translating formal tweets using context information

Eva Martnez Garcia, Cristina España-Bonet, Lluis Marques

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

Abstract

In this paper, we describe the UPC systems that participated in the TweetMT shared task. We developed two main systems that were applied to the Spanish{Catalan language pair: a state-of-the-art phrase-based statistical machine translation system and a context-aware system. In the second approach, we define the \context" for a tweet as the tweets of a user produced in the same day, and also, we study the impact of this kind of information in the final translations when using a document-level decoder. A variant of this approach considers also semantic information from bilingual embeddings.

Original languageEnglish
Title of host publicationCEUR Workshop Proceedings
PublisherCEUR-WS
Pages25-32
Number of pages8
Volume1445
Publication statusPublished - 2015
EventTweet Translation Workshop 2015, TweetMT 2015 - co-located with 31st Conference of the Spanish Society for Natural Language Processing, SEPLN 2015 - Alicante, Spain
Duration: 15 Sep 2015 → …

Other

OtherTweet Translation Workshop 2015, TweetMT 2015 - co-located with 31st Conference of the Spanish Society for Natural Language Processing, SEPLN 2015
CountrySpain
CityAlicante
Period15/9/15 → …

Fingerprint

Semantics

Keywords

  • Context Aware Translation
  • Machine Translation
  • Twitter

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Garcia, E. M., España-Bonet, C., & Marques, L. (2015). The UPC TweetMT participation: Translating formal tweets using context information. In CEUR Workshop Proceedings (Vol. 1445, pp. 25-32). CEUR-WS.

The UPC TweetMT participation : Translating formal tweets using context information. / Garcia, Eva Martnez; España-Bonet, Cristina; Marques, Lluis.

CEUR Workshop Proceedings. Vol. 1445 CEUR-WS, 2015. p. 25-32.

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

Garcia, EM, España-Bonet, C & Marques, L 2015, The UPC TweetMT participation: Translating formal tweets using context information. in CEUR Workshop Proceedings. vol. 1445, CEUR-WS, pp. 25-32, Tweet Translation Workshop 2015, TweetMT 2015 - co-located with 31st Conference of the Spanish Society for Natural Language Processing, SEPLN 2015, Alicante, Spain, 15/9/15.
Garcia EM, España-Bonet C, Marques L. The UPC TweetMT participation: Translating formal tweets using context information. In CEUR Workshop Proceedings. Vol. 1445. CEUR-WS. 2015. p. 25-32
Garcia, Eva Martnez ; España-Bonet, Cristina ; Marques, Lluis. / The UPC TweetMT participation : Translating formal tweets using context information. CEUR Workshop Proceedings. Vol. 1445 CEUR-WS, 2015. pp. 25-32
@inproceedings{8b131546fbe340e8a8b5d24063e5e4cf,
title = "The UPC TweetMT participation: Translating formal tweets using context information",
abstract = "In this paper, we describe the UPC systems that participated in the TweetMT shared task. We developed two main systems that were applied to the Spanish{Catalan language pair: a state-of-the-art phrase-based statistical machine translation system and a context-aware system. In the second approach, we define the \context{"} for a tweet as the tweets of a user produced in the same day, and also, we study the impact of this kind of information in the final translations when using a document-level decoder. A variant of this approach considers also semantic information from bilingual embeddings.",
keywords = "Context Aware Translation, Machine Translation, Twitter",
author = "Garcia, {Eva Martnez} and Cristina Espa{\~n}a-Bonet and Lluis Marques",
year = "2015",
language = "English",
volume = "1445",
pages = "25--32",
booktitle = "CEUR Workshop Proceedings",
publisher = "CEUR-WS",

}

TY - GEN

T1 - The UPC TweetMT participation

T2 - Translating formal tweets using context information

AU - Garcia, Eva Martnez

AU - España-Bonet, Cristina

AU - Marques, Lluis

PY - 2015

Y1 - 2015

N2 - In this paper, we describe the UPC systems that participated in the TweetMT shared task. We developed two main systems that were applied to the Spanish{Catalan language pair: a state-of-the-art phrase-based statistical machine translation system and a context-aware system. In the second approach, we define the \context" for a tweet as the tweets of a user produced in the same day, and also, we study the impact of this kind of information in the final translations when using a document-level decoder. A variant of this approach considers also semantic information from bilingual embeddings.

AB - In this paper, we describe the UPC systems that participated in the TweetMT shared task. We developed two main systems that were applied to the Spanish{Catalan language pair: a state-of-the-art phrase-based statistical machine translation system and a context-aware system. In the second approach, we define the \context" for a tweet as the tweets of a user produced in the same day, and also, we study the impact of this kind of information in the final translations when using a document-level decoder. A variant of this approach considers also semantic information from bilingual embeddings.

KW - Context Aware Translation

KW - Machine Translation

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=84948654385&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84948654385&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84948654385

VL - 1445

SP - 25

EP - 32

BT - CEUR Workshop Proceedings

PB - CEUR-WS

ER -