{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:13:25Z","timestamp":1750220005433,"version":"3.41.0"},"reference-count":4,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["AI Matters"],"published-print":{"date-parts":[[2021,9]]},"abstract":"<jats:p>We introduce a Model AI Assignment (Neller et al., 2021) where students combine various techniques from a deep learning course to build a denoising autoencoder (Shen, Mueller, Barzilay, &amp; Jaakkola, 2020) for news headlines. Students then use this denoising autoencoder to query similar headlines, and interpolate between headlines.<\/jats:p>\n          <jats:p>Building this denoising autoencoder requires students to apply many course concepts, including data augmentation, word and sentence embeddings, autoencoders, recurrent neural networks, sequence-to-sequence networks, and temperature. As such, this assignment can be ideal as a final assessment that synthesizes many topics.<\/jats:p>\n          <jats:p>This assignment is written in PyTorch, uses the torchtext package, and is intended to be completed on the Google Colab platform.<\/jats:p>","DOI":"10.1145\/3511322.3511327","type":"journal-article","created":{"date-parts":[[2022,1,31]],"date-time":"2022-01-31T17:36:11Z","timestamp":1643650571000},"page":"18-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AI education matters"],"prefix":"10.1145","volume":"7","author":[{"given":"Lisa","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Toronto Mississauga"}]},{"given":"Pouria","family":"Fewzee","sequence":"additional","affiliation":[{"name":"Impact Factor"}]},{"given":"Charbel","family":"Feghali","sequence":"additional","affiliation":[{"name":"University of Toronto Mississauga"}]}],"member":"320","published-online":{"date-parts":[[2022,1,31]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_2_1_1_1","DOI":"10.1609\/aaai.v34i09.7072"},{"key":"e_1_2_1_2_1","first-page":"15705","volume-title":"Proceedings of the AAAI conference on artificial intelligence (Vol. 35","author":"Neller T. W.","year":"2021","unstructured":"Neller , T. W. , Sprague , N. , Maraist , J. , Zhang , L. , Fewzee , P. , Long , D. , \u2026 others ( 2021 ). Model AI assignments 2021 . In Proceedings of the AAAI conference on artificial intelligence (Vol. 35 , pp. 15705 -- 15706 ). Neller, T. W., Sprague, N., Maraist, J., Zhang, L., Fewzee, P., Long, D., \u2026 others (2021). Model AI assignments 2021. In Proceedings of the AAAI conference on artificial intelligence (Vol. 35, pp. 15705--15706)."},{"key":"e_1_2_1_3_1","volume-title":"International conference on machine learning (pp. 8719--8729)","author":"Shen T.","year":"2020","unstructured":"Shen , T. , Mueller , J. , Barzilay , R. , & Jaakkola , T. ( 2020 ). Educating text autoencoders: Latent representation guidance via denoising . In International conference on machine learning (pp. 8719--8729) . Shen, T., Mueller, J., Barzilay, R., & Jaakkola, T. (2020). Educating text autoencoders: Latent representation guidance via denoising. In International conference on machine learning (pp. 8719--8729)."},{"key":"e_1_2_1_4_1","volume-title":"Troubleshooting deep neural networks. OpenAI.","author":"Tobin J.","year":"2019","unstructured":"Tobin , J. ( 2019 ). Troubleshooting deep neural networks. OpenAI. Retrieved from http:\/\/josh-tobin.com\/assets\/pdf\/troubleshooting-deep-neural-networks-01-19.pdf Tobin, J. (2019). Troubleshooting deep neural networks. OpenAI. Retrieved from http:\/\/josh-tobin.com\/assets\/pdf\/troubleshooting-deep-neural-networks-01-19.pdf"}],"container-title":["AI Matters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3511322.3511327","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3511322.3511327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:03Z","timestamp":1750182663000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3511322.3511327"}},"subtitle":["text denoising autoencoder for news headlines"],"short-title":[],"issued":{"date-parts":[[2021,9]]},"references-count":4,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["10.1145\/3511322.3511327"],"URL":"https:\/\/doi.org\/10.1145\/3511322.3511327","relation":{},"ISSN":["2372-3483"],"issn-type":[{"type":"electronic","value":"2372-3483"}],"subject":[],"published":{"date-parts":[[2021,9]]},"assertion":[{"value":"2022-01-31","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}