Sequence-to-Dependency Neural Machine Translation

By Shuangzhi Wu, Dongdong Zhang, Nan Yang, Mu Li, M. Zhou. 2017

102 citations recorded by the source corpus.

Nowadays a typical Neural Machine Translation (NMT) model generates translations from left to right as a linear sequence, during which latent syntactic structures of the target sentences are not explicitly concerned. Inspired by the success of using syntactic knowledge of target language for improving statistical machine translation, in this paper we propose a novel Sequence-to-Dependency Neural Machine Translation (SD-NMT) method, in which the target word sequence and its corresponding dependency structure are jointly constructed and modeled, and this structure is used as context to facilitate word generations. Experimental results show that the proposed method significantly outperforms state-of-the-art baselines on Chinese-English and Japanese-English translation tasks.

Subfields: Artificial Intelligence, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

The Hitchhiker’s Guide to Testing Statistical Significance in Natural Language Processing (2018, methodology): “Bootstrap was used with a variety of NLP tasks, including machine translation, text summarization and semantic parsing (e.g. (Koehn, 2004; Li et al., 2017; Wu et al., 2017; Ouchi et al., 2017)).”
Joint Parsing and Generation for Abstractive Summarization (2019, methodology): “Incorporating syntax is found to improve translation (Li et al. 2017a; Eriguchi, Tsuruoka, and Cho 2017; Wu et al. 2017; Wang et al. 2018).”
Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks (2018, methodology): “, 2015), or even to help next word prediction given previous words (Wu et al., 2017).”
Improved Neural Machine Translation with Chinese Phonologic Features (2018, background): “[23] proposed to jointly learn target translation and dependency parsing.”
A Tree-based Decoder for Neural Machine Translation (2018, methodology): “Neverthe-less, Wu et al. (2017) is speciﬁcally designed for dependency tree structures and is not trivially applicable to other varieties of trees such as phrase-structure trees, which have been used more widely in other works on syntax-based machine translation.”
Structural Information Preserving for Graph-to-Text Generation (2020, methodology): “Our work is remotely related to the previous efforts on string-to-tree neural machine translation (NMT) (Aharoni and Goldberg, 2017; Wu et al., 2017; Wang et al., 2018), which aims at generating target sentences with their syntactic trees.”
On the Linguistic Representational Power of Neural Machine Translation Models (2019, background): “dle long-distance dependencies. There have also been recent attempts to integrate syntax into NMT (Aharoni and Goldberg2017; Chen et al.2017;Eriguchi, Hashimoto, and Tsuruoka2016;Stahlberg et al.2016;Wu et al. 2017), but sequence-to-sequence NMT models without explicit syntax are the state-of-the-ar”