Using Perturbed Length-aware Positional Encoding for Non-autoregressive Neural Machine Translation

• URL: http://arxiv.org/abs/2107.13689v1
• Date: Thu, 29 Jul 2021 00:51:44 GMT
• Title: Using Perturbed Length-aware Positional Encoding for Non-autoregressive Neural Machine Translation
• Authors: Yui Oka, Katsuhito Sudoh, and Satoshi Nakamura
• Abstract summary: We propose sequence-level knowledge distillation (SKD) using perturbed length-aware positional encoding. Our method outperformed a standard Levenshtein Transformer by 2.5 points in bilingual evaluation understudy (BLEU) at maximum in a WMT14 German to English translation.
• Score: 32.088160646084525
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Non-autoregressive neural machine translation (NAT) usually employs sequence-level knowledge distillation using autoregressive neural machine translation (AT) as its teacher model. However, a NAT model often outputs shorter sentences than an AT model. In this work, we propose sequence-level knowledge distillation (SKD) using perturbed length-aware positional encoding and apply it to a student model, the Levenshtein Transformer. Our method outperformed a standard Levenshtein Transformer by 2.5 points in bilingual evaluation understudy (BLEU) at maximum in a WMT14 German to English translation. The NAT model output longer sentences than the baseline NAT models.

Related papers

• Revisiting Non-Autoregressive Translation at Scale [76.93869248715664]
  We systematically study the impact of scaling on non-autoregressive translation (NAT) behaviors. We show that scaling can alleviate the commonly-cited weaknesses of NAT models, resulting in better translation performance. We establish a new benchmark by validating scaled NAT models on a scaled dataset.
  arXiv  Detail & Related papers  (2023-05-25T15:22:47Z)
• Optimizing Non-Autoregressive Transformers with Contrastive Learning [74.46714706658517]
  Non-autoregressive Transformers (NATs) reduce the inference latency of Autoregressive Transformers (ATs) by predicting words all at once rather than in sequential order. In this paper, we propose to ease the difficulty of modality learning via sampling from the model distribution instead of the data distribution.
  arXiv  Detail & Related papers  (2023-05-23T04:20:13Z)
• Rephrasing the Reference for Non-Autoregressive Machine Translation [37.816198073720614]
  Non-autoregressive neural machine translation (NAT) models suffer from the multi-modality problem that there may exist multiple possible translations of a source sentence. We introduce a rephraser to provide a better training target for NAT by rephrasing the reference sentence according to the NAT output. Our best variant achieves comparable performance to the autoregressive Transformer, while being 14.7 times more efficient in inference.
  arXiv  Detail & Related papers  (2022-11-30T10:05:03Z)
• One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive Translation [13.223158914896727]
  Non-autoregressive neural machine translation (NAT) suffers from the multi-modality problem. We propose diverse distillation with reference selection ( DDRS) for NAT. DDRS achieves 29.82 BLEU with only one decoding pass on WMT14 En-De, improving the state-of-the-art performance for NAT by over 1 BLEU.
  arXiv  Detail & Related papers  (2022-05-28T04:59:33Z)
• Sequence-Level Training for Non-Autoregressive Neural Machine Translation [33.17341980163439]
  Non-Autoregressive Neural Machine Translation (NAT) removes the autoregressive mechanism and achieves significant decoding speedup. We propose using sequence-level training objectives to train NAT models, which evaluate the NAT outputs as a whole and correlates well with the real translation quality.
  arXiv  Detail & Related papers  (2021-06-15T13:30:09Z)
• Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation [98.11249019844281]
  Knowledge distillation (KD) is commonly used to construct synthetic data for training non-autoregressive translation (NAT) models. We propose reverse KD to rejuvenate more alignments for low-frequency target words. Results demonstrate that the proposed approach can significantly and universally improve translation quality.
  arXiv  Detail & Related papers  (2021-06-02T02:41:40Z)
• Understanding and Improving Lexical Choice in Non-Autoregressive Translation [98.11249019844281]
  We propose to expose the raw data to NAT models to restore the useful information of low-frequency words. Our approach pushes the SOTA NAT performance on the WMT14 English-German and WMT16 Romanian-English datasets up to 27.8 and 33.8 BLEU points, respectively.
  arXiv  Detail & Related papers  (2020-12-29T03:18:50Z)
• Multi-Task Learning with Shared Encoder for Non-Autoregressive Machine Translation [32.77372312124259]
  Non-Autoregressive machine Translation (NAT) models have demonstrated significant inference speedup but suffer from inferior translation accuracy. We propose to adopt Multi-Task learning to transfer the Autoregressive machine Translation knowledge to NAT models through encoder sharing. Experimental results on WMT14 English-German and WMT16 English-Romanian datasets show that the proposed Multi-Task NAT achieves significant improvements over the baseline NAT models.
  arXiv  Detail & Related papers  (2020-10-24T11:00:58Z)
• Glancing Transformer for Non-Autoregressive Neural Machine Translation [58.87258329683682]
  We propose a method to learn word interdependency for single-pass parallel generation models. With only single-pass parallel decoding, GLAT is able to generate high-quality translation with 8-15 times speedup.
  arXiv  Detail & Related papers  (2020-08-18T13:04:03Z)
• Task-Level Curriculum Learning for Non-Autoregressive Neural Machine Translation [188.3605563567253]
  Non-autoregressive translation (NAT) achieves faster inference speed but at the cost of worse accuracy compared with autoregressive translation (AT) We introduce semi-autoregressive translation (SAT) as intermediate tasks. SAT covers AT and NAT as its special cases. We design curriculum schedules to gradually shift k from 1 to N, with different pacing functions and number of tasks trained at the same time. Experiments on IWSLT14 De-En, IWSLT16 En-De, WMT14 En-De and De-En datasets show that TCL-NAT achieves significant accuracy improvements over previous NAT baseline
  arXiv  Detail & Related papers  (2020-07-17T06:06:54Z)
• Universal Vector Neural Machine Translation With Effective Attention [0.0]
  We propose a singular model for Neural Machine Translation based on encoder-decoder models. We introduce a neutral/universal model representation that can be used to predict more than one language.
  arXiv  Detail & Related papers  (2020-06-09T01:13:57Z)

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.