Generating Fluent Translations from Disfluent Text Without Access to Fluent References: IIT Bombay@IWSLT2020
Machine translation systems perform reasonably well when the input is well-formed speech or text. Conversational speech is spontaneous and inherently consists of many disfluencies. Producing fluent translations of disfluent source text would typically require parallel disfluent to fluent training data. However, fluent translations of spontaneous speech are an additional resource that is tedious to obtain. This work describes the submission of IIT Bombay to the Conversational Speech Translation challenge at IWSLT 2020. We specifically tackle the problem of disfluency removal in disfluent-to-fluent text-to-text translation assuming no access to fluent references during training. Common patterns of disfluency are extracted from disfluent references and a noise induction model is used to simulate them starting from a clean monolingual corpus. This synthetically constructed dataset is then considered as a proxy for labeled data during training. We also make use of additional fluent text in the target language to help generate fluent translations. This work uses no fluent references during training and beats a baseline model by a margin of 4.21 and 3.11 BLEU points where the baseline uses disfluent and fluent references, respectively. Index Terms- disfluency removal, machine translation, noise induction, leveraging monolingual data, denoising for disfluency removal.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingMachine TranslationTranslationSimilar Papers 제목 키워드 기반
Fluency Over Adequacy: A Pilot Study in Measuring User Trust in Imperfect MT
Although measuring intrinsic quality has been a key factor in the advancement of Machine Translation (MT), successfully deploying MT requires considering not just intrinsic quality but also the user experience, including…
Machine TranslationTranslationFluent Translations from Disfluent Speech in End-to-End Speech Translation
Spoken language translation applications for speech suffer due to conversational speech phenomena, particularly the presence of disfluencies. With the rise of end-to-end speech translation models, processing steps such a…
Machine Translationspeech-recognitionSpeech RecognitionTranslationTowards Fluent Translations from Disfluent Speech
When translating from speech, special consideration for conversational speech phenomena such as disfluencies is necessary. Most machine translation training data consists of well-formed written texts, causing issues when…
Machine Translationspeech-recognitionSpeech RecognitionTranslationPlanning and Generating Natural and Diverse Disfluent Texts as Augmentation for Disfluency Detection
Existing approaches to disfluency detection heavily depend on human-annotated data. Numbers of data augmentation methods have been proposed to alleviate the dependence on labeled data. However, current augmentation appro…
Data AugmentationFluent Alignment with Disfluent Judges: Post-training for Lower-resource Languages
We propose a post-training method for lower-resource languages that preserves the fluency of language models even when aligned by disfluent reward models. Preference optimization is now a well-researched topic, but previ…