{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T04:38:12Z","timestamp":1771648692872,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"01","license":[{"start":{"date-parts":[[2019,7,17]],"date-time":"2019-07-17T00:00:00Z","timestamp":1563321600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.aaai.org"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Explaining the decisions of a Deep Learning Network is imperative to safeguard end-user trust. Such explanations must be intuitive, descriptive, and faithfully explain why a model makes its decisions. In this work, we propose a framework called FLEX (Faithful Linguistic EXplanations) that generates post-hoc linguistic justifications to rationalize the decision of a Convolutional Neural Network. FLEX explains a model\u2019s decision in terms of features that are responsible for the decision. We derive a novel way to associate such features to words, and introduce a new decision-relevance metric that measures the faithfulness of an explanation to a model\u2019s reasoning. Experiment results on two benchmark datasets demonstrate that the proposed framework can generate discriminative and faithful explanations compared to state-of-the-art explanation generators. We also show how FLEX can generate explanations for images of unseen classes as well as automatically annotate objects in images.<\/jats:p>","DOI":"10.1609\/aaai.v33i01.33012539","type":"journal-article","created":{"date-parts":[[2019,9,9]],"date-time":"2019-09-09T07:45:58Z","timestamp":1568015158000},"page":"2539-2546","source":"Crossref","is-referenced-by-count":12,"title":["FLEX: Faithful Linguistic Explanations for Neural Net Based Model Decisions"],"prefix":"10.1609","volume":"33","author":[{"given":"Sandareka","family":"Wickramanayake","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wynne","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mong Li","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2019,7,17]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/4100\/3978","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/4100\/3978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,7]],"date-time":"2022-11-07T07:12:12Z","timestamp":1667805132000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/4100"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,17]]},"references-count":0,"journal-issue":{"issue":"01","published-online":{"date-parts":[[2019,7,23]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v33i01.33012539","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2019,7,17]]}}}