Dependent Multilevel Interaction Network for Natural Language Inference

  • Yun Li
  • , Yan Yang*
  • , Yong Deng
  • , Qinmin Vivian Hu
  • , Chengcai Chen
  • , Liang He
  • , Zhou Yu
  • *Corresponding author for this work

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

Abstract

Neural networks have attracted great attention for natural language inference in recent years. Interactions between the premise and the hypothesis have been proved to be effective in improving the representations. Existing methods mainly focused on a single interaction, while multiple interactions have not been well studied. In this paper, we propose a dependent multilevel interaction (DMI) Network which models multiple interactions between the premise and the hypothesis to boost the performance of natural language inference. In specific, a single-interaction unit (SIU) structure with a novel combining attention mechanism is presented to capture features in an interaction. Then, we cascade a serial of SIUs in a multilevel interaction layer to obtain more comprehensive features. Experiments on two benchmark datasets, namely SciTail and SNLI, show the effectiveness of our proposed model. Our model outperforms the state-of-the-art approaches on the SciTail dataset without using any external resources. For the SNLI dataset, our model also achieves competitive results.

Original languageEnglish
Title of host publicationArtificial Neural Networks and Machine Learning – ICANN 2019
Subtitle of host publicationText and Time Series - 28th International Conference on Artificial Neural Networks, 2019, Proceedings
EditorsIgor V. Tetko, Pavel Karpov, Fabian Theis, Vera Kurková
PublisherSpringer Verlag
Pages9-21
Number of pages13
ISBN (Print)9783030304898
DOIs
StatePublished - 2019
Event28th International Conference on Artificial Neural Networks: Workshop and Special Sessions, ICANN 2019 - Munich, Germany
Duration: 17 Sep 201919 Sep 2019

Publication series

NameLecture Notes in Computer Science
Volume11730 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference28th International Conference on Artificial Neural Networks: Workshop and Special Sessions, ICANN 2019
Country/TerritoryGermany
CityMunich
Period17/09/1919/09/19

Keywords

  • Attention mechanism
  • Deep learning
  • Sentence interaction

Fingerprint

Dive into the research topics of 'Dependent Multilevel Interaction Network for Natural Language Inference'. Together they form a unique fingerprint.

Cite this