Do Context-Aware Translation Models Pay the Right Attention?
This addresses the issue of inaccurate disambiguation in machine translation for users relying on context-aware models, representing an incremental improvement with a new dataset and analysis.
The paper tackled the problem of context-aware machine translation models failing to accurately disambiguate pronouns and polysemous words by introducing SCAT, a new English-French dataset with supporting context words for 14K translations, and found that guided attention strategies improved alignment with human translator context.
Context-aware machine translation models are designed to leverage contextual information, but often fail to do so. As a result, they inaccurately disambiguate pronouns and polysemous words that require context for resolution. In this paper, we ask several questions: What contexts do human translators use to resolve ambiguous words? Are models paying large amounts of attention to the same context? What if we explicitly train them to do so? To answer these questions, we introduce SCAT (Supporting Context for Ambiguous Translations), a new English-French dataset comprising supporting context words for 14K translations that professional translators found useful for pronoun disambiguation. Using SCAT, we perform an in-depth analysis of the context used to disambiguate, examining positional and lexical characteristics of the supporting words. Furthermore, we measure the degree of alignment between the model's attention scores and the supporting context from SCAT, and apply a guided attention strategy to encourage agreement between the two.