Tree-to-Sequence Attentional Neural Machine Translation

Abstract

Most of the existing Neural Machine Translation (NMT) models focus on the conversion of sequential data and do not directly use syntactic information. We propose a novel end-to-end syntactic NMT model, extending a sequence-to-sequence model with the source-side phrase structure. Our model has an attention mechanism that enables the decoder to generate a translated word while softly aligning it with phrases as well as words of the source sentence. Experimental results on the WAT'15 English-to-Japanese dataset demonstrate that our proposed model considerably outperforms sequence-to-sequence attentional NMT models and compares favorably with the state-of-the-art tree-to-string SMT system.

Accepted as a full paper at the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016)

References in corpus (3)

• Sequence to Sequence Learning with Neural Networks
• Effective Approaches to Attention-based Neural Machine Translation
• Neural Reranking Improves Subjective Quality of Machine Translation: NAIST at WAT2015

Cited by in corpus (25)

• Can neural machine translation do simultaneous translation?
• CODIT: Code Editing with Tree-Based Neural Models
• Code Structure Guided Transformer for Source Code Summarization
• Tree-to-tree Neural Networks for Program Translation
• A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks
• Modeling Source Syntax for Neural Machine Translation
• Learning to Parse and Translate Improves Neural Machine Translation
• Translating Phrases in Neural Machine Translation
• Automating Reading Comprehension by Generating Question and Answer Pairs
• Neural Lattice-to-Sequence Models for Uncertain Inputs
• Recurrent Graph Syntax Encoder for Neural Machine Translation
• SQL-to-Text Generation with Graph-to-Sequence Model
• Do latent tree learning models identify meaningful structure in sentences?
• Japanese Sentiment Classification using a Tree-Structured Long Short-Term Memory with Attention
• Attention-Guided Generative Adversarial Network to Address Atypical Anatomy in Modality Transfer
• Tag-Enhanced Tree-Structured Neural Networks for Implicit Discourse Relation Classification
• Neural Machine Translation with Source-Side Latent Graph Parsing
• Multi-Source Syntactic Neural Machine Translation
• Paraphrases as Foreign Languages in Multilingual Neural Machine Translation
• Syntax-Enhanced Neural Machine Translation with Syntax-Aware Word Representations
• Graph-to-Sequence Learning using Gated Graph Neural Networks
• On Tree-Based Neural Sentence Modeling
• Accelerated Reinforcement Learning for Sentence Generation by Vocabulary Prediction
• Improving Automatic Source Code Summarization via Deep Reinforcement Learning
• Comparative Code Structure Analysis using Deep Learning for Performance Prediction