publication . Conference object . Report . Other literature type . 2017

Using Coreference Links to Improve Spanish-to-English Machine Translation

Lesly Miculicich Werlen; Andrei Popescu-Belis;
Open Access
  • Published: 19 Feb 2017
  • Publisher: Association for Computational Linguistics
  • Country: Switzerland
Abstract
In this paper, we present a proof-of-concept implementation of a coreference-aware decoder for document-level machine translation. We consider that better translations should have coreference links that are closer to those in the source text, and implement this criterion in two ways. First, we define a similarity measure between source and target coreference structures, by projecting the target ones onto the source and reusing existing coreference metrics. Based on this similarity measure, we re-rank the translation hypotheses of a baseline system for each sentence. Alternatively, to address the lack of diversity of mentions in the MT hypotheses, we focus on men...
Persistent Identifiers
Subjects
free text keywords: Baseline system, Artificial intelligence, business.industry, business, Machine translation, computer.software_genre, computer, Speech recognition, Sentence, Natural language processing, Coreference, Pronoun, Source text, Computer science, Similarity measure
Related Organizations
Funded by
EC| SUMMA
Project
SUMMA
Scalable Understanding of Multilingual Media
  • Funder: European Commission (EC)
  • Project Code: 688139
  • Funding stream: H2020 | RIA
Communities
Digital Humanities and Cultural Heritage
Any information missing or wrong?Report an Issue