Rule-Based Pronominal Anaphora Treatment for Machine Translation

Abstract

In this paper we describe the rule-based MT system Its-2 developed at the University of Geneva and submitted for the shared task on pronoun translation organized within the Second DiscoMT Workshop. For improving pronoun translation, an Anaphora Resolution (AR) step based on Chomsky's Binding Theory and Hobbs' algorithm has been implemented. Since this strategy is currently restricted to 3rd person personal pronouns (i.e. they, it translated as elle, elles, il, ils only), absolute performance is affected. However, qualitative differences between the submitted system and a baseline without the AR procedure can be observed.

It-disambiguation and source-aware language models for cross-lingual pronoun prediction

“…In our opinion, this suggests that while not directly treating any of the other source-language pronouns (in the context of this shared-task, other source pronouns refers only to they), the disambiguation of it positively affects the translation of the other target-language Table 4: Final system pronouns. The pronoun it, after all, is used three times more frequently than they in the training data (Loáiciga and Wehrli, 2015). Looking at the predictions, we confirmed that both source-aware language models produced identical results almost all of the time, with the system without the labels producing more correct predictions in total.…”

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

“…ITS2 (Loáiciga and Wehrli, 2015) was a rulebased machine translation system using syntaxbased transfer. For the shared task, it was extended with an anaphora resolution component influenced by Binding Theory (Chomsky, 1981).…”

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).…”

“…As the general quality of machine translation (MT) increases, there is a growing interest in improving the translation of specific linguistic phenomena. A case in point that has been studied in the context of both statistical (Hardmeier, 2014;Guillou, 2016;Loáiciga, 2017) and neural MT (Bawden et al, 2017;Voita et al, 2018) is that of pronominal anaphora. In the simplest case, translating anaphoric pronouns requires the generation of corresponding word forms respecting the grammatical constraints on agreement in the target language, as in the following English-French example, where the correct form of the pronoun in the second sentence varies depending on which of the (equally correct) translations of the word bicycle was used in the first: However, the problem is more complex in practice because there is often no 1 : 1 correspondence between pronouns in two languages.…”