Robust Neural Machine Translation with ASR Errors
In many practical applications, neural machine translation systems have to deal with the input from automatic speech recognition (ASR) systems which may contain a certain number of errors. This leads to two problems which degrade translation performance. One is the discrepancy between the training and testing data and the other is the translation error caused by the input errors may ruin the whole translation. In this paper, we propose a method to handle the two problems so as to generate robust translation to ASR errors. First, we simulate ASR errors in the training data so that the data distribution in the training and test is consistent. Second, we focus on ASR errors on homophone words and words with similar pronunciation and make use of their pronunciation information to help the translation model to recover from the input errors. Experiments on two Chinese-English data sets show that our method is more robust to input errors and can outperform the strong Transformer baseline significantly.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine Translationspeech-recognitionSpeech RecognitionTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Measuring the Impact of Spelling Errors on the Quality of Machine Translation
In this paper we show how different types of spelling errors influence the quality of machine translation. We also propose a method to evaluate the impact of spelling errors correction on translation quality without expe…
Machine TranslationSentiment AnalysisTranslationQUARTZ: Quality-Aware Machine Translation
This paper presents QUARTZ, QUality-AwaRe machine Translation, a project led by Unbabel which aims at developing machine translation systems that are more robust and produce fewer critical errors. With QUARTZ we want to …
Machine TranslationTranslationIs This Translation Error Critical?: Classification-Based Human and Automatic Machine Translation Evaluation Focusing on Critical Errors
This paper discusses a classification-based approach to machine translation evaluation, as opposed to a common regression-based approach in the WMT Metrics task. Recent machine translation usually works well but sometime…
Machine TranslationTranslationAutomatic Correction of Human Translations
We introduce translation error correction (TEC), the task of automatically correcting human-generated translations. Imperfections in machine translations (MT) have long motivated systems for improving translations post-h…
Automatic Post-EditingTranslationSubCo: A Learner Translation Corpus of Human and Machine Subtitles
In this paper, we present a freely available corpus of human and automatic translations of subtitles. The corpus comprises, the original English subtitles (SRC), both human (HT) and machine translations (MT) into German,…
Machine TranslationTranslation