Capturing the Varieties of Natural Language Inference: A Systematic Survey of Existing Datasets and Two Novel Benchmarks

Author:

Gubelmann Reto,Katis Ioannis,Niklaus Christina,Handschuh Siegfried

Abstract

AbstractTransformer-based Pre-Trained Language Models currently dominate the field of Natural Language Inference (NLI). We first survey existing NLI datasets, and we systematize them according to the different kinds of logical inferences that are being distinguished. This shows two gaps in the current dataset landscape, which we propose to address with one dataset that has been developed in argumentative writing research as well as a new one building on syllogistic logic. Throughout, we also explore the promises of ChatGPT. Our results show that our new datasets do pose a challenge to existing methods and models, including ChatGPT, and that tackling this challenge via fine-tuning yields only partly satisfactory results.

Funder

University of St.Gallen

Publisher

Springer Science and Business Media LLC

Subject

Linguistics and Language,Philosophy,Computer Science (miscellaneous)

Reference66 articles.

1. Aristotle, J. B. (1984). Prior analytics. In J. Barnes (Ed.), The complete works of aristotle (pp. 39–113). Oxford University Press.

2. Asael, D., Ziegler, Z., & Belinkov, Y. (2021). A generative approach for mitigating structural biases in natural language inference. arXiv preprint arXiv:2108.14006

3. Baker, C. F., Fillmore, C. J., & Lowe, J. B. (1998). The berkeley framenet project. In COLING 1998 volume 1: The 17th international conference on computational linguistics.

4. Bar Haim, R., Dagan, I., Dolan, B., Ferro, L., Giampiccolo, D., Magnini, B., & Szpektor, I. (2006). The second PASCAL RTE challenge. In Proceedings of the 2nd PASCAL challenge on RTE.

5. Bentivogli, L., Clark, P., Dagan, I., & Giampiccolo, D. (2009). The 5th PASCAL recognizing textual entailment challenge. In TAC.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3