A Comprehensive Neural and Behavioral Task Taxonomy Method for Transfer Learning in NLP

  • Yunhao Zhang
  • , Chong Li
  • , Xiaohan Zhang
  • , Xinyi Dong
  • , Shaonan Wang

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

2 Citations (Scopus)

Abstract

Transfer learning is frequently utilized in scenarios with limited labeled examples, where a crucial step is to identify a related task to the target task. CogTaskonomy (Luo et al., 2022) was proposed to acquire a taxonomy of NLP tasks, specifically focusing on assessing the similarities between tasks. This method, inspired by cognitive processes, exhibits notable time efficiency. Nevertheless, it does not fully exploit the task-related information present in cognitive data and lacks a comprehensive evaluation of various types of cognitive data. To address these limitations, this paper proposes a comprehensive neural and behavioral method to investigate the relationship among NLP tasks. Our approach utilizes cognitive data, encompassing both neural data such as fMRI and EEG, as well as behavioral data including eye-tracking and semantic feature ratings. Each data modality is employed to establish a common representation space with Representation Similarity Analysis for projecting task-related representations. To fully leverage the cognitive information, we effectively extract the task-relevant information extracted from neural data through feature ranking. Experimental results on 12 NLP tasks demonstrate that our proposed method outperforms state-of-the-art methods on evaluating task similarity.

Original languageEnglish
Title of host publicationIJCNLP-AACL 2023 - 13th International JoinFindings of the Association for Computational Linguistics: IJCNLP-AACL 2023
EditorsJong C. Park, Yuki Arase, Baotian Hu, Wei Lu, Derry Wijaya, Ayu Purwarianti, Adila Alfa Krisnadhi
PublisherAssociation for Computational Linguistics (ACL)
Pages233-241
Number of pages9
ISBN (Electronic)9798891760189
DOIs
Publication statusPublished - Nov 2023
Externally publishedYes
Event13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: Findings of the Association for Computational Linguistic, IJCNLP-AACL 2023 - Nusa Dua, Bali, Indonesia
Duration: 1 Nov 20234 Nov 2023

Publication series

NameIJCNLP-AACL 2023 - 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023

Conference

Conference13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: Findings of the Association for Computational Linguistic, IJCNLP-AACL 2023
Country/TerritoryIndonesia
CityNusa Dua, Bali
Period1/11/234/11/23

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems

Fingerprint

Dive into the research topics of 'A Comprehensive Neural and Behavioral Task Taxonomy Method for Transfer Learning in NLP'. Together they form a unique fingerprint.

Cite this