Sentence-to-Label Generation Framework for Multi-task Learning of Japanese Sentence Classification and Named Entity Recognition

Chengguang Gan, Qinghao Zhang, Tatsunori Mori
6/28/2023
cs.CL

No official code found. Best implementation: ganchengguang/SLG-framework (3 stars, last commit 2024-10-18).

Abstract

Information extraction(IE) is a crucial subfield within natural language processing. In this study, we introduce a Sentence Classification and Named Entity Recognition Multi-task (SCNM) approach that combines Sentence Classification (SC) and Named Entity Recognition (NER). We develop a Sentence-to-Label Generation (SLG) framework for SCNM and construct a Wikipedia dataset containing both SC and NER. Using a format converter, we unify input formats and employ a generative model to generate SC-labels, NER-labels, and associated text segments. We propose a Constraint Mechanism (CM) to improve generated format accuracy. Our results show SC accuracy increased by 1.13 points and NER by 1.06 points in SCNM compared to standalone tasks, with CM raising format accuracy from 63.61 to 100. The findings indicate mutual reinforcement effects between SC and NER, and integration enhances both tasks' performance.

View on arXivView PDF

Code Implementations(1)

ganchengguang/SLG-frameworkCommunity100%

paper code

30PythonJul 1, 20232 years ago

Similar Papers

Mutual Reinforcement Effects in Japanese Sentence Classification and Named Entity Recognition Tasks

88% match2023

Easy-to-Hard Learning for Information Extraction

83% match1 repo142023

Universal Information Extraction with Meta-Pretrained Self-Retrieval

83% match2023

R³-NL2GQL: A Model Coordination and Knowledge Graph Alignment Approach for NL2GQL

83% match1 repo1032023

Large Language Models for Generative Information Extraction: A Survey

82% match1 repo1.1k2023

CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors

81% match1 repo422023

Cite this paper

@article{gan2023sentencetolabel,
  title  = {Sentence-to-Label Generation Framework for Multi-task Learning of Japanese Sentence Classification and Named Entity Recognition},
  author = {Chengguang Gan and Qinghao Zhang and Tatsunori Mori},
  year   = {2023},
  eprint = {2306.15978},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.15978v1}
}

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/2306.15978.svg)](https://codeofpaper.com/paper/2306.15978)

Discussion