mlsanityData to 7 Oct 2026

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

arXiv 2306.15978 ↗First posted 28 Jun 2023cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 10 of its 19 references that are in the map. First posted on arXiv 28 Jun 2023.

Builds on

10 of 19 references.

References · 10

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2016Neural Architectures for Named Entity Recognitioncited by 548
  3. 2015Bidirectional LSTM-CRF Models for Sequence Taggingcited by 544
  4. 2022Unified Structure Generation for Universal Information Extractioncited by 220
  5. 2021A Unified Generative Framework for Various NER Subtaskscited by 141
  6. 2015A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classificationcited by 92
  7. 2021GenIE: Generative Information Extractioncited by 53
  8. 2022InstructionNER: A Multi-Task Instruction-Based Generative Framework for Few-shot NERcited by 31
  9. 2021LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Promptingcited by 27
  10. 2022Few-shot Named Entity Recognition with Self-describing Networkscited by 16

Built on by

Cited by year

Citing papers per year: 2023: 3.

3 papers.

  1. 2023USA: Universal Sentiment Analysis Model & Construction of Japanese Sentiment Text Classification and Part of Speech Datasetcited by 6
  2. 2023GIELLM: Japanese General Information Extraction Large Language Model Utilizing Mutual Reinforcement Effectcited by 6
  3. 2023Mutual Reinforcement Effects in Japanese Sentence Classification and Named Entity Recognition Taskscited by 0