Exploiting Cross-Sentence Context for Neural Machine Translation
Longyue Wang,Zhaopeng Tu,Andy Way,Qun Liu +3 more
- pp 2826-2831
Reads0
Chats0
TLDR
This article proposed a cross-sentence context-aware approach and investigated the influence of historical contextual information on the performance of neural machine translation (NMT) in Chinese-English translation.Abstract:
In translation, considering the document
as a whole can help to resolve ambiguities
and inconsistencies. In this paper, we propose a cross-sentence context-aware approach and investigate the influence of historical contextual information on the performance of neural machine translation
(NMT). First, this history is summarized
in a hierarchical way. We then integrate
the historical representation into NMT in
two strategies: 1) a warm-start of encoder and decoder states, and 2) an auxiliary context source for updating decoder
states. Experimental results on a large
Chinese-English translation task show that
our approach significantly improves upon
a strong attention-based NMT system by
up to +2.1 BLEU points.read more
Citations
More filters
Proceedings ArticleDOI
Context-Aware Neural Machine Translation Learns Anaphora Resolution
TL;DR: The authors introduced a context-aware NMT model to control the flow of information from the extended context to the translation model, which can be used to improve pronoun translation in English-Russian subtitles.
Posted Content
Multilingual Denoising Pre-training for Neural Machine Translation
Yinhan Liu,Jiatao Gu,Naman Goyal,Xian Li,Sergey Edunov,Marjan Ghazvininejad,Michael Lewis,Luke Zettlemoyer +7 more
TL;DR: This paper proposed mBART, a sequence-to-sequence denoising auto-encoder pre-trained on large-scale monolingual corpora in many languages using the BART objective.
Proceedings ArticleDOI
Evaluating Discourse Phenomena in Neural Machine Translation
TL;DR: This paper investigated the performance of multi-encoder NMT models trained on subtitles for English to French and found that decoding the concatenation of the previous and current sentence leads to good performance.
Proceedings ArticleDOI
Improving the Transformer Translation Model with Document-Level Context.
TL;DR: This work extends the Transformer model with a new context encoder to represent document-level context, which is then incorporated into the original encoder and decoder, and introduces a two-step training method to take full advantage of abundant sentence-level parallel corpora and limited document- level parallel Corpora.
Proceedings Article
Search Engine Guided Neural Machine Translation
TL;DR: Empirical evaluation on three language pairs shows that the proposed approach significantly outperforms the baseline approach and the improvement is more significant when more relevant sentence pairs were retrieved.
References
More filters
Proceedings ArticleDOI
Bleu: a Method for Automatic Evaluation of Machine Translation
TL;DR: This paper proposed a method of automatic machine translation evaluation that is quick, inexpensive, and language-independent, that correlates highly with human evaluation, and that has little marginal cost per run.
Proceedings Article
Neural Machine Translation by Jointly Learning to Align and Translate
TL;DR: It is conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and it is proposed to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly.
Proceedings Article
Sequence to Sequence Learning with Neural Networks
TL;DR: The authors used a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector.
Proceedings ArticleDOI
Effective Approaches to Attention-based Neural Machine Translation
TL;DR: A global approach which always attends to all source words and a local one that only looks at a subset of source words at a time are examined, demonstrating the effectiveness of both approaches on the WMT translation tasks between English and German in both directions.
Posted Content
A Neural Conversational Model
Oriol Vinyals,Quoc V. Le +1 more
TL;DR: A simple approach to conversational modeling which uses the recently proposed sequence to sequence framework, and is able to extract knowledge from both a domain specific dataset, and from a large, noisy, and general domain dataset of movie subtitles.