DEEP: DEnoising Entity Pre-training for Neural Machine Translation

• URL: http://arxiv.org/abs/2111.07393v1
• Date: Sun, 14 Nov 2021 17:28:09 GMT
• Title: DEEP: DEnoising Entity Pre-training for Neural Machine Translation
• Authors: Junjie Hu, Hiroaki Hayashi, Kyunghyun Cho, Graham Neubig
• Abstract summary: 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.
• Score: 123.6686940355937
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: It has been shown that machine translation models usually generate poor translations for named entities that are infrequent in the training corpus. Earlier named entity translation methods mainly focus on phonetic transliteration, which ignores the sentence context for translation and is limited in domain and language coverage. To address this limitation, 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. Besides, we investigate a multi-task learning strategy that finetunes a pre-trained neural machine translation model on both entity-augmented monolingual data and parallel data to further improve entity translation. Experimental results on three language pairs demonstrate that \method results in significant improvements over strong denoising auto-encoding baselines, with a gain of up to 1.3 BLEU and up to 9.2 entity accuracy points for English-Russian translation.

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)
• Exploring Linguistic Similarity and Zero-Shot Learning for Multilingual Translation of Dravidian Languages [0.34998703934432673]
  We build a single-decoder neural machine translation system for Dravidian-Dravidian multilingual translation. Our model achieves scores within 3 BLEU of large-scale pivot-based models when it is trained on 50% of the language directions.
  arXiv  Detail & Related papers  (2023-08-10T13:38:09Z)
• Extract and Attend: Improving Entity Translation in Neural Machine Translation [141.7840980565706]
  We propose an Extract-and-Attend approach to enhance entity translation in NMT. The proposed method is effective on improving both the translation accuracy of entities and the overall translation quality.
  arXiv  Detail & Related papers  (2023-06-04T03:05:25Z)
• CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence Translation [113.99145386490639]
  Cross-lingual NER can transfer knowledge between languages via aligned cross-lingual representations or machine translation results. We propose a Cross-lingual Entity Projection framework (CROP) to enable zero-shot cross-lingual NER. We adopt a multilingual labeled sequence translation model to project the tagged sequence back to the target language and label the target raw sentence.
  arXiv  Detail & Related papers  (2022-10-13T13:32:36Z)
• Unsupervised Neural Machine Translation with Generative Language Models Only [19.74865387759671]
  We show how to derive state-of-the-art unsupervised neural machine translation systems from generatively pre-trained language models. Our method consists of three steps: few-shot amplification, distillation, and backtranslation.
  arXiv  Detail & Related papers  (2021-10-11T17:35:34Z)
• Distributionally Robust Multilingual Machine Translation [94.51866646879337]
  We propose a new learning objective for Multilingual neural machine translation (MNMT) based on distributionally robust optimization. We show how to practically optimize this objective for large translation corpora using an iterated best response scheme. Our method consistently outperforms strong baseline methods in terms of average and per-language performance under both many-to-one and one-to-many translation settings.
  arXiv  Detail & Related papers  (2021-09-09T03:48:35Z)
• On the Language Coverage Bias for Neural Machine Translation [81.81456880770762]
  Language coverage bias is important for neural machine translation (NMT) because the target-original training data is not well exploited in current practice. By carefully designing experiments, we provide comprehensive analyses of the language coverage bias in the training data. We propose two simple and effective approaches to alleviate the language coverage bias problem.
  arXiv  Detail & Related papers  (2021-06-07T01:55:34Z)
• Incorporating Bilingual Dictionaries for Low Resource Semi-Supervised Neural Machine Translation [5.958653653305609]
  We incorporate widely available bilingual dictionaries that yield word-by-word translations to generate synthetic sentences. This automatically expands the vocabulary of the model while maintaining high quality content.
  arXiv  Detail & Related papers  (2020-04-05T02:14:14Z)

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.