paper-with-me

홈 › Papers

Towards Linear Time Neural Machine Translation with Capsule Networks

2018-11-01 · IJCNLP 2019 11 · Mingxuan Wang, Jun Xie, Zhixing Tan, Jinsong Su, Deyi Xiong, Lei LI

In this study, we first investigate a novel capsule network with dynamic routing for linear time Neural Machine Translation (NMT), referred as \textsc{CapsNMT}. \textsc{CapsNMT} uses an aggregation mechanism to map the source sentence into a matrix with pre-determined size, and then applys a deep LSTM network to decode the target sequence from the source representation. Unlike the previous work \cite{sutskever2014sequence} to store the source sentence with a passive and bottom-up way, the dynamic routing policy encodes the source sentence with an iterative process to decide the credit attribution between nodes from lower and higher layers. \textsc{CapsNMT} has two core properties: it runs in time that is linear in the length of the sequences and provides a more flexible way to select, represent and aggregates the part-whole information of the source sentence. On WMT14 English-German task and a larger WMT14 English-French task, \textsc{CapsNMT} achieves comparable results with the state-of-the-art NMT systems. To the best of our knowledge, this is the first work that capsule networks have been empirically investigated for sequence to sequence problems.

📄 PDF Abstract BibTeX arXiv:1811.00287

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTSentenceTranslation

Methods 이 논문이 사용한 방법론

Capsule Network A capsule is an activation vector that basically executes on its inputs some complex internal computations. Length of these activation vectors signifies the probability of…
Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Capsule-Transformer for Neural Machine Translation

2020-04-30 · Sufeng Duan, Juncheng Cao, Hai Zhao

Transformer hugely benefits from its key design of the multi-head self-attention network (SAN), which extracts information from various perspectives through transforming the given input into different subspaces. However,…

Machine TranslationTranslation

Enhancing Context Modeling with a Query-Guided Capsule Network for Document-level Translation

2019-09-02 · IJCNLP 2019 11 · Zhengxin Yang, Jinchao Zhang, Fandong Meng, Shuhao Gu 외

Context modeling is essential to generate coherent and consistent translation for Document-level Neural Machine Translations. The widely used method for document-level translation usually compresses the context informati…

Translation

Improving Multi-Head Attention with Capsule Networks

2019-08-31 · Shuhao Gu, Yang Feng

Multi-head attention advances neural machine translation by working out multiple versions of attention in different subspaces, but the neglect of semantic overlapping between subspaces increases the difficulty of transla…

ClusteringMachine TranslationTranslation

A quantifiable testing of global translational invariance in Convolutional and Capsule Networks

2019-05-01 · ICLR 2019 5 · Weikai Qi

We design simple and quantifiable testing of global translation-invariance in deep learning models trained on the MNIST dataset. Experiments on convolutional and capsules neural networks show that both models have poor …

Data AugmentationTranslation

Dynamic Context-guided Capsule Network for Multimodal Machine Translation

2020-09-04 · Huan Lin, Fandong Meng, Jinsong Su, Yongjing Yin 외

Multimodal machine translation (MMT), which mainly focuses on enhancing text-only translation with visual features, has attracted considerable attention from both computer vision and natural language processing communiti…

DecoderMachine TranslationMultimodal Machine TranslationRepresentation Learning+1