{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T02:47:05Z","timestamp":1748314025285},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7]]},"abstract":"<jats:p>Transformer and its variants, built based on attention mechanisms, have recently achieved remarkable performance in many NLP tasks. Most existing works on Transformer explanation tend to reveal and utilize the attention matrix with human subjective intuitions in a qualitative manner. However, the huge size of dimensions directly challenges these methods to quantitatively analyze the attention matrix. Therefore, in this paper, we propose a novel reinforcement learning (RL) based framework for Transformer explanation via attention matrix, namely AttExplainer. The RL agent learns to perform step-by-step masking operations by observing the change in attention matrices. We have adapted our method to two scenarios, perturbation-based model explanation and text adversarial attack. Experiments on three widely used text classification benchmarks validate the effectiveness of the proposed method compared to state-of-the-art baselines. Additional studies show that our method is highly transferable and consistent with human intuition. The code of this paper is available at https:\/\/github.com\/niuzaisheng\/AttExplainer .<\/jats:p>","DOI":"10.24963\/ijcai.2022\/102","type":"proceedings-article","created":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T22:55:56Z","timestamp":1657925756000},"page":"724-731","source":"Crossref","is-referenced-by-count":5,"title":["AttExplainer: Explain Transformer via Attention by Reinforcement Learning"],"prefix":"10.24963","author":[{"given":"Runliang","family":"Niu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Jilin University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhepei","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University"},{"name":"Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"31","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2022","name":"Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}","start":{"date-parts":[[2022,7,23]]},"theme":"Artificial Intelligence","location":"Vienna, Austria","end":{"date-parts":[[2022,7,29]]}},"container-title":["Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T07:07:42Z","timestamp":1658128062000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2022\/102"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2022\/102","relation":{},"subject":[],"published":{"date-parts":[[2022,7]]}}}