Pronoun Translation in English-French Machine Translation: An Analysis of Error Types

By Christian Hardmeier, Liane Guillou. 2018

9 citations recorded by the source corpus.

Pronouns are a long-standing challenge in machine translation. We present a study of the performance of a range of rule-based, statistical and neural MT systems on pronoun translation based on an extensive manual evaluation using the PROTEST test suite, which enables a fine-grained analysis of different pronoun types and sheds light on the difficulties of the task. We find that the rule-based approaches in our corpus perform poorly as a result of oversimplification, whereas SMT and early NMT systems exhibit significant shortcomings due to a lack of awareness of the functional and referential properties of pronouns. A recent Transformer-based NMT system with cross-sentence context shows very promising results on non-anaphoric pronouns and intra-sentential anaphora, but there is still considerable room for improvement in examples with cross-sentence dependencies.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Toward Gender-Inclusive Coreference Resolution (2019, background): “In machine translation, producing correct gendered forms in gender languages often requires coreference to have been solved [Guillou 2012; Hardmeier and Federico 2010; Hardmeier and Guillou 2018; Mitkov 1999].”