DiSAN: directional self-attention network for RNN/CNN-free language understanding

Tao Shen, Jing Jiang, Tianyi Zhou, Shirui Pan, Guodong Long, Chengqi Zhang

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

147 Citations (Scopus)

Abstract

Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively. Attention mechanisms have recently attracted enormous interest due to their highly parallelizable computation, significantly less training time, and flexibility in modeling dependencies. We propose a novel attention mechanism in which the attention between elements from input sequence(s) is directional and multi-dimensional (i.e., feature-wise). A light-weight neural net, “Directional Self-Attention Network (DiSAN)”, is then proposed to learn sentence embedding, based solely on the proposed attention without any RNN/CNN structure. DiSAN is only composed of a directional self-attention with temporal order encoded, followed by a multi-dimensional attention that compresses the sequence into a vector representation. Despite its simple form, DiSAN outperforms complicated RNN models on both prediction quality and time efficiency. It achieves the best test accuracy among all sentence encoding methods and improves the most recent best result by 1.02% on the Stanford Natural Language Inference (SNLI) dataset, and shows state-of-the-art test accuracy on the Stanford Sentiment Treebank (SST), Multi-Genre natural language inference (MultiNLI), Sentences Involving Compositional Knowledge (SICK), Customer Review, MPQA, TREC question-type classification and Subjectivity (SUBJ) datasets.

Original languageEnglish
Title of host publicationThe Thirty-Second AAAI Conference on Artificial Intelligence
EditorsSheila McIlraith, Kilian Weinberger
Place of PublicationPalo Alto CA USA
PublisherAssociation for the Advancement of Artificial Intelligence (AAAI)
Pages5446-5455
Number of pages10
ISBN (Electronic)9781577358008
Publication statusPublished - 2018
Externally publishedYes
EventAAAI Conference on Artificial Intelligence 2018 - New Orleans, United States of America
Duration: 2 Feb 20187 Feb 2018
Conference number: 32nd
https://aaai.org/Conferences/AAAI-18/

Conference

ConferenceAAAI Conference on Artificial Intelligence 2018
Abbreviated titleAAAI 2018
CountryUnited States of America
CityNew Orleans
Period2/02/187/02/18
Internet address

Cite this