A Case Study on Contextual Machine Translation in a Professional Scenario of Subtitling

Incorporating extra-textual context such as film metadata into the machine translation (MT) pipeline can enhance translation quality, as indicated by automatic evaluation in recent work. However, the positive impact of such systems in industry remains unproven. We report on an industrial case study carried out to investigate the benefit of MT in a professional scenario of translating TV subtitles with a focus on how leveraging extra-textual context impacts post-editing. We found that post-editors marked significantly fewer context-related errors when correcting the outputs of MTCue, the context-aware model, as opposed to non-contextual models. We also present the results of a survey of the employed post-editors, which highlights contextual inadequacy as a significant gap consistently observed in MT. Our findings strengthen the motivation for further work within fully contextual MT.

Personalised Language Modelling of Screen Characters Using Rich Metadata Annotations

Personalisation of language models for dialogue sensitises them to better capture the speaking patterns of people of specific characteristics, and/or in specific environments. However, rich character annotations are difficult to come by and to successfully leverage. In this work, we release and describe a novel set of manual annotations for 863 speakers from the popular Cornell Movie Dialog Corpus, including features like characteristic quotes and character descriptions, and a set of six automatically extracted metadata for over 95% of the featured films. We perform extensive experiments on two corpora and show that such annotations can be effectively used to personalise language models, reducing perplexity by up to 8.5%. Our method can be applied even zero-shot for speakers for whom no prior training data is available, by relying on combinations of characters' demographic characteristics. Since collecting such metadata is costly, we also contribute a cost-benefit analysis to highlight which annotations were most cost-effective relative to the reduction in perplexity.