A Chinese Textual Entailment Recognition Method Incorporating Semantic Role and Self-Attention

ZHANG Zhi-chang; ZENG Yang-yang; PANG Ya-li

doi:10.3969/j.issn.0372-2112.2020.11.010

您当前的位置：

首页 >

文章列表页 >

A Chinese Textual Entailment Recognition Method Incorporating Semantic Role and Self-Attention

更新时间：2025-12-08

- A Chinese Textual Entailment Recognition Method Incorporating Semantic Role and Self-Attention
- Acta Electronica Sinica Vol. 48, Issue 11, Pages: 2162-2169(2020)
- 作者机构：
  
  西北师范大学计算机科学与工程学院,甘肃,兰州,730000
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61762081, No.61662067, No.61662068);Key Research and Development Project of Gansu Province (No.17YF1GA016)
- DOI：10.3969/j.issn.0372-2112.2020.11.010
  CLC： TP391.1TP183
- Published Online：25 November 2020，
  
  Published：2020
- 稿件说明：
移动端阅览
ZHANG Zhi-chang, ZENG Yang-yang, PANG Ya-li. A Chinese Textual Entailment Recognition Method Incorporating Semantic Role and Self-Attention[J]. Acta Electronica Sinica, 2020, 48(11): 2162-2169.
DOI：

ZHANG Zhi-chang, ZENG Yang-yang, PANG Ya-li. A Chinese Textual Entailment Recognition Method Incorporating Semantic Role and Self-Attention[J]. Acta Electronica Sinica, 2020, 48(11): 2162-2169. DOI： 10.3969/j.issn.0372-2112.2020.11.010.

摘要

文本蕴含识别旨在识别两个给定句子之间的逻辑关系.本文通过构造语义角色和自注意力机制融合模块，把句子的深层语义信息与Transformer模型的编码部分相结合，从而增强自注意力机制捕获句子语义的能力.针对中文文本蕴含识别在数据集上存在规模小和噪声大的问题，使用大规模预训练语言模型能够提升模型在小规模数据集上的识别性能.实验结果表明，提出的方法在第十七届中国计算语言学大会中文文本蕴含识别评测数据集CNLI上的准确率达到了80.28%.

Abstract

Recognizing textual entailment is intended to infer the logical relationship between two given sentences. In this paper

we incorporate the deep semantic information of sentences and the encoder of Transformer by constructing the SRL-Attention fusion module

and it effectively improves the ability of self-attention mechanism to capture sentence semantics. Furthermore

concerning the small scale and high noise problems on the dataset

we use large-scale pre-trained language model improving the recognition performance of model on small-scale dataset. Experimental results show that the accuracy of our model on the dataset CNLI

it is released as Chinese textual entailment recognition evaluation corpus at the 17th China National Conference on Computational Linguistics

reaches 80.28%.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Enhancing Multimodal Aspect-Based Sentiment Analysis with Adaptive Noise and Aspect Graph Association Learning

Chinese Long Text Summarization with Guided Attention

The Multi-Behavior Graph Contrastive Learning Recommendation Method with Self-Attention Mechanism

User Trajectory Identification Based on Expandable Self-Attention Spatio-Temporal Graph Convolutional Neural Networks

A Rumor Detection Approach Based on Multi-Feature Propagation Tree

Related Author

HUANG Chen

LIU Hui-jie

ZHANG Yan

YANG Chao

SONG Jian-hua

GUO Zhe

ZHANG Zhi-bo

ZHOU Wei-jie

Related Institution

School of Cyber Science and Technology, Hubei University

Hubei Province Project of Key Research Institute of Humanities and Social Sciences at Universities-RCIMPE

Hubei Key Laboratory of Big Data Intelligent Analysis and Application

Key Laboratory of Intelligent Sensing System and Security, Ministry of Education

School of Computer Science, Hubei University

⁰