paper-with-me

홈 › Papers

Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation

2021-05-11 · Findings (ACL) 2021 8 · Shun-Po Chuang, Yung-Sung Chuang, Chih-Chiang Chang, Hung-Yi Lee

We study the possibilities of building a non-autoregressive speech-to-text translation model using connectionist temporal classification (CTC), and use CTC-based automatic speech recognition as an auxiliary task to improve the performance. CTC's success on translation is counter-intuitive due to its monotonicity assumption, so we analyze its reordering capability. Kendall's tau distance is introduced as the quantitative metric, and gradient-based visualization provides an intuitive way to take a closer look into the model. Our analysis shows that transformer encoders have the ability to change the word order and points out the future research direction that worth being explored more on non-autoregressive speech translation.

📄 PDF Abstract BibTeX arXiv:2105.04840

Code (1)

voidism/NAR-ST 공식 구현 pytorch

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSpeech-to-TextSpeech-to-Text TranslationTranslation

Similar Papers 제목 키워드 기반

Guiding Non-Autoregressive Neural Machine Translation Decoding with Reordering Information

2019-11-06 · Qiu Ran, Yankai Lin, Peng Li, Jie zhou

Non-autoregressive neural machine translation (NAT) generates each target word in parallel and has achieved promising inference acceleration. However, existing NAT models still have a big gap in translation quality compa…

Machine TranslationTranslation

ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation

2022-10-08 · COLING 2022 10 · Cunxiao Du, Zhaopeng Tu, Longyue Wang, Jing Jiang

Recently, a new training oaxe loss has proven effective to ameliorate the effect of multimodality for non-autoregressive translation (NAT), which removes the penalty of word order errors in the standard cross-entropy los…

Machine TranslationSentenceTranslation

Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translation

2022-10-08 · Chenze Shao, Yang Feng

Non-autoregressive translation (NAT) models are typically trained with the cross-entropy loss, which forces the model outputs to be aligned verbatim with the target sentence and will highly penalize small shifts in word …

Machine TranslationSentenceTranslation

MMPE: A Multi-Modal Interface using Handwriting, Touch Reordering, and Speech Commands for Post-Editing Machine Translation

2020-07-01 · ACL 2020 6 · Nico Herbig, Santanu Pal, Tim D{\"u}wel, Kalliopi Meladaki 외

The shift from traditional translation to post-editing (PE) of machine-translated (MT) text can save time and reduce errors, but it also affects the design of translation interfaces, as the task changes from mainly gener…

Machine TranslationTranslation

Alignment-based reordering for SMT

2012-05-01 · LREC 2012 5 · Maria Holmqvist, Sara Stymne, Lars Ahrenberg, Magnus Merkel

We present a method for improving word alignment quality for phrase-based statistical machine translation by reordering the source text according to the target word order suggested by an initial word alignment. The reord…

Machine TranslationPart-Of-Speech TaggingTranslationWord Alignment