Sequence-to-Dependency Neural Machine Translation

Wu, Shuangzhi; Zhang, Dongdong; Yang, Nan; Li, Mu; Zhou, Ming

doi:10.18653/v1/p17-1065

Cited by 105 publications

(61 citation statements)

References 18 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this work, we model syntactic information of target tokens using an additional sequence of variables, which captures the syntactic choices 1 at (a) Full co-dependence model. (Wang et al, 2018a;Wu et al, 2017;Aharoni and Goldberg, 2017). (c) LaSyn, our latent syntax model that uses non-sequential latent variables for exhaustive search of latent states.…”

Section: A Latent Syntax Model For Decodingmentioning

confidence: 99%

“…Aharoni et al (2017) treated constituency trees as sequential strings and trained a Seq2Seq model to translate source sentences into these tree sequences. Wang et al (2018a) and Wu et al (2017) proposed to use two RNNs, a Rule RNN and a Word RNN, to generate a target sentence and its corresponding tree structure. Gu et al (2018) proposed a model to translate and parse at the same time.…”

Section: Model Bleumentioning

confidence: 99%

See 1 more Smart Citation

Latent Part-of-Speech Sequences for Neural Machine Translation

Yang

Liu

Xie

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

show abstract

Section: A Latent Syntax Model For Decodingmentioning

confidence: 99%

Section: Model Bleumentioning

confidence: 99%

Latent Part-of-Speech Sequences for Neural Machine Translation

Yang

Liu

Xie

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

show abstract

“…Recent efforts have demonstrated that incorporating linguistic information can be useful in NMT [7,12,15,17,22,23]. Since the source sentence is definitive and easy to attach extra information, it is a straightforward way to improve the translation performance by using the source side features [12,17].…”

Section: Related Workmentioning

confidence: 99%

Case-Sensitive Neural Machine Translation

Shi

Huang

Jian

et al. 2020

Advances in Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Even as an important lexical information for Latin languages, word case is often ignored in machine translation. According to observations, the translation performance drops significantly when we introduce case-sensitive evaluation metrics. In this paper, we introduce two types of case-sensitive neural machine translation (NMT) approaches to alleviate the above problems: i) adding case tokens into the decoding sequence, and ii) adopting case prediction to the conventional NMT. Our proposed approaches incorporate case information to the NMT decoder by jointly learning target word generation and word case prediction. We compare our approaches with multiple kinds of baselines including NMT with naive case-restoration methods and analyze the impacts of various setups on our approaches. Experimental results on three typical translation tasks (Zh-En, En-Fr, En-De) show that our proposed methods lead to the improvements up to 2.5, 1.0 and 0.5 in case-sensitive BLEU scores respectively. Further analyses also illustrate the inherent reasons why our approaches lead to different improvements on different translation tasks.

show abstract

“…Unlike prior work on syntactic decoders designed for utilizing a specific type of syntactic information (Wu et al, 2017), TrDec is a flexible NMT model that can utilize any tree structure. Here we consider two categories of tree structures:…”

Section: Tree Structuresmentioning

confidence: 99%

A Tree-based Decoder for Neural Machine Translation

Wang¹,

Pham²,

Yin³

et al. 2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Recent advances in Neural Machine Translation (NMT) show that adding syntactic information to NMT systems can improve the quality of their translations. Most existing work utilizes some specific types of linguisticallyinspired tree structures, like constituency and dependency parse trees. This is often done via a standard RNN decoder that operates on a linearized target tree structure. However, it is an open question of what specific linguistic formalism, if any, is the best structural representation for NMT. In this paper, we (1) propose an NMT model that can naturally generate the topology of an arbitrary tree structure on the target side, and (2) experiment with various target tree structures. Our experiments show the surprising result that our model delivers the best improvements with balanced binary trees constructed without any linguistic knowledge; this model outperforms standard seq2seq models by up to 2.1 BLEU points, and other methods for incorporating target-side syntax by up to 0.7 BLEU. 1

show abstract

Sequence-to-Dependency Neural Machine Translation

Cited by 105 publications

References 18 publications

Latent Part-of-Speech Sequences for Neural Machine Translation

Latent Part-of-Speech Sequences for Neural Machine Translation

Case-Sensitive Neural Machine Translation

A Tree-based Decoder for Neural Machine Translation

Contact Info

Product

Resources

About