Secoco: Self-Correcting Encoding for Neural Machine Translation
This paper presents Self-correcting Encoding (Secoco), a framework that effectively deals with input noise for robust neural machine translation by introducing self-correcting predictors. Different from previous robust approaches, Secoco enables NMT to explicitly correct noisy inputs and delete specific errors simultaneously with the translation decoding process. Secoco is able to achieve significant improvements over strong baselines on two real-world test sets and a benchmark WMT dataset with good interpretability. We will make our code and dataset publicly available soon.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationNMTTranslationSimilar Papers 제목 키워드 기반
MuseCoco: Generating Symbolic Music from Text
Generating music from text descriptions is a user-friendly mode since the text is a relatively easy interface for user engagement. While some approaches utilize texts to control music audio generation, editing musical el…
AttributeAudio GenerationMusic GenerationHow to Learn in a Noisy World? Self-Correcting the Real-World Data Noise on Machine Translation
The massive amounts of web-mined parallel data contain large amounts of noise. Semantic misalignment, as the primary source of the noise, poses a challenge for training machine translation systems. In this paper, we firs…
Machine TranslationSemantic SimilaritySemantic Textual SimilarityTranslationCorrecting Length Bias in Neural Machine Translation
We study two problems in neural machine translation (NMT). First, in beam search, whereas a wider beam should in principle help translation, it often hurts NMT. Second, NMT has a tendency to produce translations that are…
Machine TranslationNMTTranslationPrompting Large Language Models with Human Error Markings for Self-Correcting Machine Translation
While large language models (LLMs) pre-trained on massive amounts of unpaired language data have reached the state-of-the-art in machine translation (MT) of general domain texts, post-editing (PE) is still required to co…
Machine TranslationTranslationRethink about the Word-level Quality Estimation for Machine Translation from Human Judgement
Word-level Quality Estimation (QE) of Machine Translation (MT) aims to find out potential translation errors in the translated sentence without reference. Typically, conventional works on word-level QE are designed to pr…
Machine TranslationSentenceTAGTranslation