Syntax-aware Natural Language Inference with Graph Matching Networks

The task of entailment judgment aims to determine whether a hypothesis is true (entailment), false (contradiction), or undetermined (neutral) given a premise. While previous methods strike successful in several benchmarks and even exceed the human baseline, recent researches show that it remains arg...

Full description

Saved in:
Bibliographic Details
Main Authors: Lin, Yan-Tong, Wu, Meng-Tse, Su, Keh-Yih
Format: Conference Proceeding
Language:English
Subjects:
Artificial intelligence
Benchmark testing
Context modeling
dependency tree
Encoding
graph neural networks
natural language inference
Natural languages
recognize textual entailment
Task analysis
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The task of entailment judgment aims to determine whether a hypothesis is true (entailment), false (contradiction), or undetermined (neutral) given a premise. While previous methods strike successful in several benchmarks and even exceed the human baseline, recent researches show that it remains arguable if the methods learn the statistical bias in the datasets. In this paper, we propose the syntax-aware Natural Language Inference (SynNLI) model, which utilizes graph matching networks to obtain syntax-guided contextualized representation while aligning the premise and the hypothesis accordingly. We show that the proposed method outperforms multiple baseline models on MNLI develop set, and visualize the model internal behavior.
ISSN:2376-6824
DOI:10.1109/TAAI51410.2020.00024