Findings of the 2016 WMT Shared Task on Cross-lingual Pronoun Prediction

By Liane Guillou, Christian Hardmeier, Preslav Nakov, Sara Stymne, Jörg Tiedemann, Yannick Versley, Mauro Cettolo, Bonnie L. Webber, Andrei Popescu-Belis. 2019

55 citations recorded by the source corpus.

We describe the design, the evaluation setup, and the results of the 2016 WMT shared task on cross-lingual pronoun prediction. This is a classification task in which participants are asked to provi ...

Subfields: Natural Language Processing

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Findings of the 2016 Conference on Machine Translation (2016, background): “…tasks that are described in separate papers in these proceedings: • tuning (Jawaid et al., 2016) • metrics (Bojar et al., 2016b) • cross-lingual pronoun prediction (Guillou et al., 2016) • multimodal machine translation and crosslin- gual image description (Specia et al., 2016) • bilingual…”
Using Coreference Links to Improve Spanish-to-English Machine Translation (2017, result): “The improvement of pronoun translation was only marginal with respect to a baseline SMT system in the 2015 shared task (Hardmeier et al., 2015), while the 2016 shared task was only aiming at pronoun prediction given source texts and lemmatized reference translations (Guillou et al., 2016).”
Gender bias amplification during Speed-Quality optimization in Neural Machine Translation (2021, unknown): “Furthermore, these biases probably evade detection in shared tasks that focus on quality without a speed incentive (Guillou et al., 2016) because participants would not typically optimize their systems for speed.”
Robustness in Coreference Resolution (2020, background): “…of using coreference information in various applications is receiving more attention recently, e.g. in machine translation (Hardmeier et al., 2015; Guillou et al., 2016), question answering (Choi et al., 2017), text compression (Dhingra et al., 2017), text summarization (Durrett et al., 2016),…”
Findings of the 2017 DiscoMT Shared Task on Cross-lingual Pronoun Prediction (2017, methodology): “Similarly to the setup of the WMT 2016 shared task (Guillou et al., 2016), the participants had to predict a target-language pronoun given a source-language pronoun in the context of a sentence, which in turn was given in the context of a full document.”
On Integrating Discourse in Machine Translation (2017, background): “More recently, pronoun prediction in general has been the focus of increased attention, resulting in the creation of a specific WMT Shared Task on Cross-lingual Pronoun Prediction (Guillou et al., 2016), and to the development of resources such as test suites (Guillou and Hardmeier, 2016) for the au”
Validation of an Automatic Metric for the Accuracy of Pronoun Translation (APT) (2017, background): “Guillou (2016) argues that a correct translation of pronouns, in case several options are possible (i.e. in the case of translation divergences), requires the identiﬁcation of their function, and then of their antecedent (if they are referential), with which they typically agree in gender and…”