paper-with-me

Papers

Multi-Granularity Self-Attention for Neural Machine Translation

2019-09-05 · IJCNLP 2019 11 · Jie Hao, Xing Wang, Shuming Shi, Jinfeng Zhang, Zhaopeng Tu

Current state-of-the-art neural machine translation (NMT) uses a deep multi-head self-attention network with no explicit phrase information. However, prior work on statistical machine translation has shown that extending the basic translation unit from words to phrases has produced substantial improvements, suggesting the possibility of improving NMT performance from explicit modeling of phrases. In this work, we present multi-granularity self-attention (Mg-Sa): a neural network that combines multi-head self-attention and phrase modeling. Specifically, we train several attention heads to attend to phrases in either n-gram or syntactic formalism. Moreover, we exploit interactions among phrases to enhance the strength of structure modeling - a commonly-cited weakness of self-attention. Experimental results on WMT14 English-to-German and NIST Chinese-to-English translation tasks show the proposed approach consistently improves performance. Targeted linguistic analysis reveals that Mg-Sa indeed captures useful phrase information at various levels of granularities.

📄 PDF Abstract BibTeX arXiv:1909.02222

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTTranslation

Similar Papers 제목 키워드 기반

Combining Character and Word Information in Neural Machine Translation Using a Multi-Level Attention

2018-06-01 · NAACL 2018 6 · Huadong Chen, Shu-Jian Huang, David Chiang, Xin-yu Dai 외

Natural language sentences, being hierarchical, can be represented at different levels of granularity, like words, subwords, or characters. But most neural machine translation systems require the sentence to be represent…

DecoderMachine TranslationSentenceTranslation

Knowledge Graph Enhanced Neural Machine Translation via Multi-task Learning on Sub-entity Granularity

2020-12-01 · COLING 2020 8 · Yang Zhao, Lu Xiang, Junnan Zhu, Jiajun Zhang 외

Previous studies combining knowledge graph (KG) with neural machine translation (NMT) have two problems: i) Knowledge under-utilization: they only focus on the entities that appear in both KG and training sentence pairs,…

Machine TranslationMulti-Task LearningNMTSentence+1

Hie-BART: Document Summarization with Hierarchical BART

2021-06-01 · NAACL 2021 4 · Kazuki Akiyama, Akihiro Tamura, Takashi Ninomiya

This paper proposes a new abstractive document summarization model, hierarchical BART (Hie-BART), which captures hierarchical structures of a document (i.e., sentence-word structures) in the BART model. Although the exis…

Document SummarizationMachine TranslationSentenceTranslation

Area Attention

2018-10-23 · ICLR 2019 5 · Yang Li, Lukasz Kaiser, Samy Bengio, Si Si

Existing attention mechanisms are trained to attend to individual items in a collection (the memory) with a predefined, fixed granularity, e.g., a word token or an image grid. We propose area attention: a way to attend t…

Image CaptioningMachine TranslationTranslation

Weighted Transformer Network for Machine Translation

2017-11-06 · ICLR 2018 1 · Karim Ahmed, Nitish Shirish Keskar, Richard Socher

State-of-the-art results on neural machine translation often use attentional sequence-to-sequence models with some form of convolution or recursion. Vaswani et al. (2017) propose a new architecture that avoids recurrence…

Machine TranslationTranslation