Local Interpretations for Explainable Natural Language Processing: A Survey

Author:

Luo Siwen1ORCID,Ivison Hamish2ORCID,Han Soyeon Caren3ORCID,Poon Josiah4ORCID

Affiliation:

1. The University of Western Australia, Perth, Australia

2. University of Washington, Seattle, United States

3. The University of Melbourne, Melbourne, Australia

4. The University of Sydney, Sydney, Australia

Abstract

As the use of deep learning techniques has grown across various fields over the past decade, complaints about the opaqueness of the black-box models have increased, resulting in an increased focus on transparency in deep learning models. This work investigates various methods to improve the interpretability of deep neural networks for Natural Language Processing (NLP) tasks, including machine translation and sentiment analysis. We provide a comprehensive discussion on the definition of the term interpretability and its various aspects at the beginning of this work. The methods collected and summarised in this survey are only associated with local interpretation and are specifically divided into three categories: (1) interpreting the model’s predictions through related input features; (2) interpreting through natural language explanation; (3) probing the hidden states of models and word representations.

Publisher

Association for Computing Machinery (ACM)

Reference200 articles.

1. Peeking inside the black-box: A survey on explainable artificial intelligence (XAI);Adadi Amina;IEEE Access,2018

2. Fine-grained analysis of sentence embeddings using auxiliary prediction tasks;Adi Yossi;arXiv preprint arXiv:1608.04207,2016

3. Shourya Aggarwal, Divyanshu Mandowara, Vishwajeet Agrawal, Dinesh Khandelwal, Parag Singla, and Dinesh Garg. 2021. Explanations for commonsenseQA: New dataset and models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, 3050–3065. DOI:10.18653/v1/2021.acl-long.238

4. Tariq Alhindi, Savvas Petridis, and Smaranda Muresan. 2018. Where is your evidence: Improving fact-checking by justification modeling. In Proceedings of the 1st Workshop on Fact Extraction and VERification (FEVER’18). Association for Computational Linguistics, 85–90. DOI:10.18653/v1/W18-5513

5. David Alvarez-Melis and Tommi Jaakkola. 2017. A causal framework for explaining the predictions of black-box sequence-to-sequence models. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. 412–421.

Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Classifying Ambiguous Requirements: An Explainable Approach in Railway Industry;2024 IEEE 32nd International Requirements Engineering Conference Workshops (REW);2024-06-24

2. Multimodal Large Language Models in Healthcare: Applications, Challenges, and Future Outlook (Preprint);Journal of Medical Internet Research;2024-04-13

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