Inference Helps PLMs’ Conceptual Understanding: Improving the Abstract Inference Ability with Hierarchical Conceptual Entailment Graphs

Page view(s)
24
Checked on Sep 04, 2025
Inference Helps PLMs’ Conceptual Understanding: Improving the Abstract Inference Ability with Hierarchical Conceptual Entailment Graphs
Title:
Inference Helps PLMs’ Conceptual Understanding: Improving the Abstract Inference Ability with Hierarchical Conceptual Entailment Graphs
Journal Title:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Keywords:
Publication Date:
27 November 2024
Citation:
Li, J., Li, R., Li, X., Chai, Q., & Pan, J. Z. (2024). Inference Helps PLMs’ Conceptual Understanding: Improving the Abstract Inference Ability with Hierarchical Conceptual Entailment Graphs. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 22088–22104. https://doi.org/10.18653/v1/2024.emnlp-main.1233
Abstract:
The abstract inference capability of the Language Model plays a pivotal role in boosting its generalization and reasoning prowess in Natural Language Inference (NLI). Entailment graphs are crafted precisely for this purpose, focusing on learning entailment relations among predicates. Yet, prevailing approaches overlook the *polysemy* and *hierarchical nature of concepts* during entity conceptualization. This oversight disregards how arguments might entail differently across various concept levels, thereby missing potential entailment connections. To tackle this hurdle, we introduce the *concept pyramid* and propose the HiCon-EG (Hierarchical Conceptual Entailment Graph) framework, which organizes arguments hierarchically, delving into entailment relations at diverse concept levels. By learning entailment relationships at different concept levels, the model is guided to better understand concepts so as to improve its abstract inference capabilities. Our method enhances scalability and efficiency in acquiring common-sense knowledge through leveraging statistical language distribution instead of manual labeling, Experimental results show that entailment relations derived from HiCon-EG significantly bolster abstract detection tasks. Our code is available at https://github.com/SXUCFN/HiCon-EG
License type:
Attribution 4.0 International (CC BY 4.0)
Funding Info:
This research / project is supported by the National Natural Science Foundation of China - NA
Grant Reference no. : 61936012

This research / project is supported by the Science and Technology Cooperation and Exchange Special Project of ShanXi Province - NA
Grant Reference no. : 202204041101016

This research / project is supported by the Chang Jiang Scholars Program - NA
Grant Reference no. : J2019032

This research / project is supported by the Key Research and Development Program of Shanxi Province - NA
Grant Reference no. : 202102020101008
Description:
ACL materials are Copyright © 1963–2025 ACL; other materials are copyrighted by their respective copyright holders. Permission is granted to make copies for the purposes of teaching and research. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.
ISSN:
NIL
Files uploaded:

File Size Format Action
2024emnlp-main1233.pdf 5.81 MB PDF Open