Neural Natural Language Inference Models Enhanced with External Knowledge

Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Diana Inkpen, Si Wei
11/12/2017
cs.CL

Official code: lukecq1231/kim (54 stars, Apache-2.0, last commit 2022-10-07).

Abstract

Modeling natural language inference is a very challenging task. With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which have shown to achieve the state-of-the-art performance. Although there exist relatively large annotated data, can machines learn all knowledge needed to perform natural language inference (NLI) from these data? If not, how can neural-network-based NLI models benefit from external knowledge and how to build NLI models to leverage it? In this paper, we enrich the state-of-the-art neural natural language inference models with external knowledge. We demonstrate that the proposed models improve neural NLI models to achieve the state-of-the-art performance on the SNLI and MultiNLI datasets.

View on arXivView PDF

Code Implementations(1)

lukecq1231/kimOfficial100%
Apache-2.0

Knowledge-based Inference Model

5413Java, ShellMay 10, 20184 years agoApache-2.0

Similar Papers

Enhanced LSTM for Natural Language Inference

87% match1 repo2672016

Learning Natural Language Inference with LSTM

85% match1 repo2842015

Atomic Inference for NLI with Generated Facts as Atoms

84% match1 repo2023

Mitigating Data Scarcity for Large Language Models

83% match2023

Compositional Language Understanding with Text-based Relational Reasoning

83% match1 repo202018

End-to-End Bias Mitigation by Modelling Biases in Corpora

83% match1 repo172019

Cite this paper

@article{chen2017neural,
  title  = {Neural Natural Language Inference Models Enhanced with External Knowledge},
  author = {Qian Chen and Xiaodan Zhu and Zhen-Hua Ling and Diana Inkpen and Si Wei},
  year   = {2017},
  eprint = {1711.04289},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1711.04289}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1711.04289.svg)](https://codeofpaper.com/paper/1711.04289)

Discussion