{"type":"ScholarlyArticle","title":"The Good, the Bad, and the Explainer: A Tool for Contrastive Explanations of Text Classifiers","authors":[{"name":"Lorenzo Malandri","slug":"lorenzo-malandri","given":"Lorenzo","family":"Malandri","affiliation":"Dept of Statistics and Quantitative Methods , University of Milano Bicocca , Italy; CRISP Research Centre crispresearch.eu , University of Milano Bicocca , Italy"},{"name":"Fabio Mercorio","slug":"fabio-mercorio","given":"Fabio","family":"Mercorio","affiliation":"Dept of Statistics and Quantitative Methods , University of Milano Bicocca , Italy; CRISP Research Centre crispresearch.eu , University of Milano Bicocca , Italy"},{"name":"Mario Mezzanzanica","slug":"mario-mezzanzanica","given":"Mario","family":"Mezzanzanica","affiliation":"Dept of Statistics and Quantitative Methods , University of Milano Bicocca , Italy; CRISP Research Centre crispresearch.eu , University of Milano Bicocca , Italy"},{"name":"Navid Nobani","slug":"navid-nobani","given":"Navid","family":"Nobani","affiliation":"Dept of Informatics, Systems and Communication , University of Milano Bicocca , Italy"},{"name":"Andrea Seveso","slug":"andrea-seveso","given":"Andrea","family":"Seveso","affiliation":"Dept of Informatics, Systems and Communication , University of Milano Bicocca , Italy; CRISP Research Centre crispresearch.eu , University of Milano Bicocca , Italy"}],"abstract":"In the last few years, we have been witnessing the increasing deployment of machine learning-based systems, which act as black boxes whose behaviour is hidden to end-users. As a side-effect, this contributes to increasing the need for explainable methods and tools to support the coordination between humans and ML models towards collaborative decision-making. In this paper, we demonstrate ContrXT, a novel tool that computes the differences in the classification logic of two distinct trained models, reasoning on their symbolic representation through Binary Decision Diagrams.\r\nContrXT is available as a pip package and API.","doi":"10.24963/ijcai.2022/858","url":"https://ijcai.org/proceedings/2022/858","pdf":"https://ijcai.org/proceedings/2022/0858.pdf","markdown":"https://ijcai.org/proceedings/2022/858.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/858","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Demo Track","track":"Demo Track","number":858,"pages":{"first":5936,"last":5939},"keywords":["Natural Language Processing: Interpretability and Analysis of Models for NLP","AI Ethics, Trust, Fairness: Explainability and Interpretability"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38987202","length_sec":102,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985345","length_sec":337,"provider":"slideslive"}],"references":[{"position":1,"raw":"Bryant, 1986","title":null,"authors":"Bryant","year":"1986","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"Randal E Bryant. Graph-based algorithms for boolean function manipulation. IEEE Transactions on Computers, 1986.","title":"Graph-based algorithms for boolean function manipulation","authors":"Randal E Bryant","year":"1986","venue":"IEEE Transactions on Computers","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Burkart and Huber, 2021] Nadia Burkart and Marco F Hu- ber. A survey on the explainability of supervised machine learning. JAIR, 70:245-317, 2021.","title":"A survey on the explainability of supervised machine learning","authors":"Nadia Burkart, Marco F Huber","year":"2021","venue":"JAIR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cho et al., 2014] Kyunghyun Cho, Bart Van Merriënboer, Dzmitry Bahdanau, and Yoshua Bengio. On the proper- ties of neural machine translation: Encoder-decoder ap- proaches. arXiv preprint arXiv:1409.1259, 2014.","title":"On the properties of neural machine translation: Encoder-decoder approaches","authors":"Cho","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Devlin et al., 2019] Jacob Devlin, Ming-Wei Chang, Ken- ton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understand- ing. In NAACL, pages 4171-4186, 2019.","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","authors":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova","year":"2019","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Gatt and Krahmer, 2018] Albert Gatt and Emiel Krahmer. Survey of the state of the art in natural language genera- tion: Core tasks, applications and evaluation. JAIR, 61, 2018.","title":"Survey of the state of the art in natural language generation: Core tasks, applications and evaluation","authors":"Krahmer Gatt, Albert Gatt, Emiel Krahmer","year":"2018","venue":"JAIR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Grinberg, 2018] Miguel Grinberg. Flask web development: developing web applications with python. \" O'Reilly Me- dia, Inc.\", 2018.","title":"Flask web development: developing web applications with python","authors":"Miguel Grinberg, Grinberg","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hall et al., 2017] Patrick Hall, Navdeep Gill, Megan Kurka, and Wen Phan. Machine learning interpretability with h2o driverless ai. H2O. ai. URL: http://docs. h2o. ai/driverless-ai/latest-stable/docs/booklets/MLIBooklet. pdf, 2017.","title":"Machine learning interpretability with h2o driverless ai. H2O. ai","authors":"Patrick Hall, Navdeep Gill, Megan Kurka, Wen Phan","year":"2017","venue":null,"doi":null,"url":"http://docs.h2o.ai/driverless-ai/latest-stable/docs/booklets/MLIBooklet.pdf","internal_url":null},{"position":9,"raw":"[Jin et al., 2016] Peng Jin, Yue Zhang, Xingyuan Chen, and Yunqing Xia. Bag-of-embeddings for text classification. In IJCAI, pages 2824-2830, 2016.","title":"Bag-of-embeddings for text classification","authors":"Jin Peng, Yue Zhang, Xingyuan Chen, Yunqing Xia","year":"2016","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2016/401"},{"position":10,"raw":"[Krippendorff, 2004] Klaus Krippendorff. Reliability in con- tent analysis: Some common misconceptions and recom- mendations. Human communication research, 30(3):411- 433, 2004.","title":"Reliability in content analysis: Some common misconceptions and recommendations","authors":"Klaus Krippendorff, Krippendorff","year":"2004","venue":"Human communication research","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Malandri et al., 2022a] Lorenzo Malandri, Fabio Mercorio, Mario Mezzanzanica, Navid Nobani, and Andrea Seveso. ContrXT: Generating contrastive explanations from any text classifier. Information Fusion, 81:103-115, 2022.","title":"ContrXT: Generating contrastive explanations from any text classifier","authors":"Malandri","year":"2022","venue":"Information Fusion","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Malandri et al., 2022b] Lorenzo Malandri, Fabio Mercorio, Mario Mezzanzanica, Navid Nobani, and Andrea Seveso. ContrXT PyPI project page. https://pypi.org/project/ contrxt/, 2022. Accessed: 2022-05-20.","title":"ContrXT PyPI project page","authors":"Malandri","year":"2022","venue":null,"doi":null,"url":"https://pypi.org/project/contrxt/,2022","internal_url":null},{"position":13,"raw":"[Malandri et al., 2022c] Lorenzo Malandri, Fabio Mercorio, Mario Mezzanzanica, Navid Nobani, and Andrea Seveso. ContrXT web page. https://ContrXT.ai, 2022. Accessed: 2022-05-20.","title":"ContrXT web page","authors":"Malandri","year":"2022","venue":null,"doi":null,"url":"https://ContrXT.ai,2022","internal_url":null},{"position":14,"raw":"[Miller, 2019] Tim Miller. Explanation in artificial intelli- gence: Insights from the social sciences. Artificial Intelli- gence, 267, 2019.","title":"Explanation in artificial intelligence: Insights from the social sciences","authors":"Tim Miller, Miller","year":"2019","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Mueller et al., 2019] Shane T Mueller, Robert R Hoffman, William Clancey, Abigail Emrey, and Gary Klein. Expla- nation in human-ai systems: A literature meta-review, syn- opsis of key ideas and publications, and bibliography for explainable ai. arXiv preprint arXiv:1902.01876, 2019.","title":"Explanation in human-ai systems: A literature meta-review, synopsis of key ideas and publications, and bibliography for explainable ai","authors":"Robert R Shane T Mueller, William Hoffman, Abigail Clancey, Gary Emrey, Klein","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Palan and Schitter, 2018] Stefan Palan and Christian Schit- ter. Prolific. ac-a subject pool for online experiments. Journal of Behavioral and Experimental Finance, 17:22- 27, 2018.","title":"Stefan Palan and Christian Schitter. Prolific. ac-a subject pool for online experiments","authors":"Schitter Palan","year":"2018","venue":"Journal of Behavioral and Experimental Finance","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Rajaraman and Ullman, 2011] Anand Rajaraman and Jef- frey David Ullman. Mining of massive datasets. Cam- bridge University Press, 2011.","title":"Mining of massive datasets","authors":"Ullman Rajaraman, Anand Rajaraman, Jeffrey David Ullman","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ribeiro et al., 2016] Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. Why should i trust you?: Explaining the predictions of any classifier. In ACM-SIGKDD, pages 1135-1144, 2016.","title":"Why should i trust you?: Explaining the predictions of any classifier","authors":"Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin","year":"2016","venue":"ACM-SIGKDD","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Rosenthal et al., 2016] Stephanie Rosenthal, Sai P Selvaraj, and Manuela M Veloso. Verbalization: Narration of au- tonomous robot experience. In IJCAI, volume 16, pages 862-868, 2016.","title":"Verbalization: Narration of autonomous robot experience","authors":"Stephanie Rosenthal, P Sai, Manuela M Selvaraj, Veloso","year":"2016","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2016/127"},{"position":20,"raw":"[Sebastiani, 2002] Fabrizio Sebastiani. Machine learning in automated text categorization. CSUR, 34(1), 2002.","title":"Machine learning in automated text categorization","authors":"Fabrizio Sebastiani","year":"2002","venue":"CSUR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Van Bouwel and Weber, 2002] Jeroen Van Bouwel and Erik Weber. Remote causes, bad explanations? JTSB, 32(4), 2002.","title":"Remote causes, bad explanations?","authors":"Van Bouwel, Weber ;, Jeroen Van Bouwel, Erik Weber","year":"2002","venue":"JTSB","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}