paper-with-me

홈 › Papers

Extract and Attend: Improving Entity Translation in Neural Machine Translation

2023-06-04 · Zixin Zeng, Rui Wang, Yichong Leng, Junliang Guo, Xu Tan, Tao Qin, Tie-Yan Liu

While Neural Machine Translation(NMT) has achieved great progress in recent years, it still suffers from inaccurate translation of entities (e.g., person/organization name, location), due to the lack of entity training instances. When we humans encounter an unknown entity during translation, we usually first look up in a dictionary and then organize the entity translation together with the translations of other parts to form a smooth target sentence. Inspired by this translation process, we propose an Extract-and-Attend approach to enhance entity translation in NMT, where the translation candidates of source entities are first extracted from a dictionary and then attended to by the NMT model to generate the target sentence. Specifically, the translation candidates are extracted by first detecting the entities in a source sentence and then translating the entities through looking up in a dictionary. Then, the extracted candidates are added as a prefix of the decoder input to be attended to by the decoder when generating the target sentence through self-attention. Experiments conducted on En-Zh and En-Ru demonstrate that the proposed method is effective on improving both the translation accuracy of entities and the overall translation quality, with up to 35% reduction on entity error rate and 0.85 gain on BLEU and 13.8 gain on COMET.

📄 PDF Abstract BibTeX arXiv:2306.02242

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderMachine TranslationNMTSentenceTranslation

Similar Papers 제목 키워드 기반

Entity-level Cross-modal Learning Improves Multi-modal Machine Translation

2021-11-01 · Findings (EMNLP) 2021 11 · Xin Huang, Jiajun Zhang, Chengqing Zong

Multi-modal machine translation (MMT) aims at improving translation performance by incorporating visual information. Most of the studies leverage the visual information through integrating the global image features as au…

Machine TranslationRepresentation LearningTranslation

Improving the Quality of MT Output using Novel Name Entity Translation Scheme

2013-10-02 · Deepti Bhalla, Nisheeth Joshi, Iti Mathur

This paper presents a novel approach to machine translation by combining the state of art name entity translation scheme. Improper translation of name entities lapse the quality of machine translated output. In this work…

Machine TranslationMiscellaneousTranslationTransliteration

DEEP: DEnoising Entity Pre-training for Neural Machine Translation

2022-01-16 · ACL ARR January 2022 1 · Anonymous

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 transl…

DenoisingMachine TranslationMulti-Task LearningSentence+2

DEEP: DEnoising Entity Pre-training for Neural Machine Translation

2021-11-14 · ACL 2022 5 · Junjie Hu, Hiroaki Hayashi, Kyunghyun Cho, Graham Neubig

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 transl…

DenoisingMachine TranslationMulti-Task LearningSentence+2

Learning When to Attend for Neural Machine Translation

2017-05-31 · Junhui Li, Muhua Zhu

In the past few years, attention mechanisms have become an indispensable component of end-to-end neural machine translation models. However, previous attention models always refer to some source words when predicting a t…

DecoderMachine TranslationTranslation