Automatic Post-Editing for the DiscoMT Pronoun Translation Task

Abstract

This paper describes an automated postediting submission to the DiscoMT 2015 shared task on pronoun translation. Postediting is achieved by applying pronounspecific rules to the output of an Englishto-French phrase-based SMT system.

What is it? Disambiguating the different readings of the pronoun ‘it’

“…In the context of machine translation, work by Le Nagard and Koehn (2010); Novák et al (2013); Guillou (2015) and Loáiciga et al (2016) have also considered disambiguating the function of the pronoun 'it' in the interest of improving pronoun translation into different languages.…”

Pronoun-Focused MT and Cross-Lingual Pronoun Prediction: Findings of the 2015 DiscoMT Shared Task on Pronoun Translation

“…The IDIAP (Luong et al, 2015) and the AUTO-POSTEDIT (Guillou, 2015) submissions were phrase-based, built using the same training and tuning resources and methods as the official baseline. Both adopted a two-pass approach involving an automatic post-editing step to correct the pronoun translations output by the baseline system, and both of them relied on the Stanford anaphora resolution software (Lee et al, 2011).…”

Automatic Reference-Based Evaluation of Pronoun Translation Misses the Point

“…Our dataset contains human judgements on the performance of nine MT systems on the translation of the 250 pronouns in the PROTEST test suite. The systems include five submissions to the DiscoMT 2015 shared task on pronoun translation (Hardmeier et al, 2015) -four phrase-based SMT systems AUTO-POSTEDIT (Guillou, 2015), UU-HARDMEIER (Hardmeier et al, 2015), IDIAP (Luong et al, 2015), UU-TIEDEMANN (Tiedemann, 2015), a rule-based system ITS2 (Loáiciga and Wehrli, 2015), and the shared task baseline (also phrase-based SMT). Three NMT systems are included for comparison: LIMSI (Bawden et al, 2017), NYU (Jean et al, 2014), and YANDEX (Voita et al, 2018).…”