{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/saliency-learning-teaching-the-model-where-to","title":"Saliency Learning: Teaching the Model Where to Pay Attention","arxiv_id":"1902.08649","date":"2019-02-22","proceeding":"NAACL 2019 6","authors":["Reza Ghaeini","Xiaoli Z. Fern","Hamed Shahbazi","Prasad Tadepalli"],"abstract":"Deep learning has emerged as a compelling solution to many NLP tasks with\nremarkable performances. However, due to their opacity, such models are hard to\ninterpret and trust. Recent work on explaining deep models has introduced\napproaches to provide insights toward the model's behaviour and predictions,\nwhich are helpful for assessing the reliability of the model's predictions.\nHowever, such methods do not improve the model's reliability. In this paper, we\naim to teach the model to make the right prediction for the right reason by\nproviding explanation training and ensuring the alignment of the model's\nexplanation with the ground truth explanation. Our experimental results on\nmultiple tasks and datasets demonstrate the effectiveness of the proposed\nmethod, which produces more reliable predictions while delivering better\nresults compared to traditionally trained models.","url_abs":"http://arxiv.org/abs/1902.08649v3","url_pdf":"http://arxiv.org/pdf/1902.08649v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"saliency-learning-teaching-the-model-where-to","repo_url":"https://github.com/chord-chen-30/uimer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.08649","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}