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

By Lesly Miculicich, Andrei Popescu-Belis. 2017

28 citations recorded by the source corpus.

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 mention pairs and integrate their coreference scores with MT ones, resulting in post-editing decisions for mentions. The experimental results for Spanish to English MT on the AnCora-ES corpus show that the second approach yields a substantial increase in the accuracy of pronoun translation, with BLEU scores remaining constant.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Document-Level Neural Machine Translation with Hierarchical Attention Networks (2018, methodology): “However, most of the work explicitly models discourse phenomena (Sim Smith, 2017) such as lexical co-hesion (Meyer and Popescu-Belis, 2012; Xiong et al., 2013; Lo´aiciga and Grisot, 2016; Pu et al., 2017; Mascarell, 2017), coherence (Born et al., 2017), and coreference (Rios Gonzales and Tuggener, 2”