Simultaneous Neural Machine Translation with Constituent Label Prediction

• URL: http://arxiv.org/abs/2110.13480v1
• Date: Tue, 26 Oct 2021 08:23:20 GMT
• Title: Simultaneous Neural Machine Translation with Constituent Label Prediction
• Authors: Yasumasa Kano, Katsuhito Sudoh, Satoshi Nakamura
• Abstract summary: Simultaneous translation is a task in which translation begins before the speaker has finished speaking. We propose a couple of simple decision rules using the label of the next constituent predicted by incremental constituent label prediction. In experiments on English-to-Japanese simultaneous translation, the proposed method outperformed baselines in the quality-latency trade-off.
• Score: 35.74159659906497
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Simultaneous translation is a task in which translation begins before the speaker has finished speaking, so it is important to decide when to start the translation process. However, deciding whether to read more input words or start to translate is difficult for language pairs with different word orders such as English and Japanese. Motivated by the concept of pre-reordering, we propose a couple of simple decision rules using the label of the next constituent predicted by incremental constituent label prediction. In experiments on English-to-Japanese simultaneous translation, the proposed method outperformed baselines in the quality-latency trade-off.

Related papers

• Crossing the Threshold: Idiomatic Machine Translation through Retrieval Augmentation and Loss Weighting [66.02718577386426]
  We provide a simple characterization of idiomatic translation and related issues. We conduct a synthetic experiment revealing a tipping point at which transformer-based machine translation models correctly default to idiomatic translations. To improve translation of natural idioms, we introduce two straightforward yet effective techniques.
  arXiv  Detail & Related papers  (2023-10-10T23:47:25Z)
• Decomposed Prompting for Machine Translation Between Related Languages using Large Language Models [55.35106713257871]
  We introduce DecoMT, a novel approach of few-shot prompting that decomposes the translation process into a sequence of word chunk translations. We show that DecoMT outperforms the strong few-shot prompting BLOOM model with an average improvement of 8 chrF++ scores across the examined languages.
  arXiv  Detail & Related papers  (2023-05-22T14:52:47Z)
• Anticipation-free Training for Simultaneous Translation [70.85761141178597]
  Simultaneous translation (SimulMT) speeds up the translation process by starting to translate before the source sentence is completely available. Existing methods increase latency or introduce adaptive read-write policies for SimulMT models to handle local reordering and improve translation quality. We propose a new framework that decomposes the translation process into the monotonic translation step and the reordering step.
  arXiv  Detail & Related papers  (2022-01-30T16:29:37Z)
• DEEP: DEnoising Entity Pre-training for Neural Machine Translation [123.6686940355937]
  It has been shown that machine translation models usually generate poor translations for named entities that are infrequent in the training corpus. We propose DEEP, a DEnoising Entity Pre-training method that leverages large amounts of monolingual data and a knowledge base to improve named entity translation accuracy within sentences.
  arXiv  Detail & Related papers  (2021-11-14T17:28:09Z)
• Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement [38.89496608319392]
  We propose an algorithm to reorder and refine the target side of a full sentence translation corpus. The words/phrases between the source and target sentences are aligned largely monotonically, using word alignment and non-autoregressive neural machine translation. The proposed approach improves BLEU scores and resulting translations exhibit enhanced monotonicity with source sentences.
  arXiv  Detail & Related papers  (2021-10-18T22:51:21Z)
• Facilitating Terminology Translation with Target Lemma Annotations [4.492630871726495]
  We train machine translation systems using a source-side data augmentation method that annotates randomly selected source language words with their target language lemmas. Experiments on terminology translation into the morphologically complex Baltic and Uralic languages show an improvement of up to 7 BLEU points over baseline systems. Results of the human evaluation indicate a 47.7% absolute improvement over the previous work in term translation accuracy when translating into Latvian.
  arXiv  Detail & Related papers  (2021-01-25T12:07:20Z)
• SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation [23.685648804345984]
  Simultaneous text translation and end-to-end speech translation have recently made great progress but little work has combined these tasks together. We investigate how to adapt simultaneous text translation methods such as wait-k and monotonic multihead attention to end-to-end simultaneous speech translation by introducing a pre-decision module. A detailed analysis is provided on the latency-quality trade-offs of combining fixed and flexible pre-decision with fixed and flexible policies.
  arXiv  Detail & Related papers  (2020-11-03T22:47:58Z)
• Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer Reorderings [24.997435410680378]
  We propose a novel method that rewrites the target side of existing full-sentence corpora into simultaneous-style translation. Experiments on Zh->En and Ja->En simultaneous translation show substantial improvements with the addition of these generated pseudo-references.
  arXiv  Detail & Related papers  (2020-10-21T19:03:06Z)
• Neural Syntactic Preordering for Controlled Paraphrase Generation [57.5316011554622]
  Our work uses syntactic transformations to softly "reorder'' the source sentence and guide our neural paraphrasing model. First, given an input sentence, we derive a set of feasible syntactic rearrangements using an encoder-decoder model. Next, we use each proposed rearrangement to produce a sequence of position embeddings, which encourages our final encoder-decoder paraphrase model to attend to the source words in a particular order.
  arXiv  Detail & Related papers  (2020-05-05T09:02:25Z)
• Re-translation versus Streaming for Simultaneous Translation [14.800214853561823]
  We study a problem in which revisions to the hypothesis beyond strictly appending words are permitted. In this setting, we compare custom streaming approaches to re-translation. We find re-translation to be as good or better than state-of-the-art streaming systems.
  arXiv  Detail & Related papers  (2020-04-07T18:27:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.