no code implementations • COLING 2020 • Aparna Garimella, Carmen Banea, Nabil Hossain, Rada Mihalcea
The subjective nature of humor makes computerized humor generation a challenging task.
no code implementations • SEMEVAL 2020 • Nabil Hossain, John Krumm, Michael Gamon, Henry Kautz
The second subtask is to predict, for a pair of edited versions of the same original headline, which is the funnier version.
no code implementations • ACL 2020 • Nabil Hossain, Marjan Ghazvininejad, Luke Zettlemoyer
Retrieve-and-edit seq2seq methods typically retrieve an output from the training set and learn a model to edit it to produce the final output.
no code implementations • 31 May 2020 • Aparna Garimella, Carmen Banea, Nabil Hossain, Rada Mihalcea
The subjective nature of humor makes computerized humor generation a challenging task.
2 code implementations • ACL 2020 • Nabil Hossain, John Krumm, Tanvir Sajed, Henry Kautz
Building datasets of creative text, such as humor, is quite challenging.
no code implementations • NAACL 2019 • Nabil Hossain, John Krumm, Michael Gamon
We introduce, release, and analyze a new dataset, called Humicroedit, for research in computational humor.
no code implementations • 1 Jun 2019 • Nabil Hossain, John Krumm, Michael Gamon
We introduce, release, and analyze a new dataset, called Humicroedit, for research in computational humor.
no code implementations • EMNLP 2017 • Nabil Hossain, John Krumm, V, Lucy erwende, Eric Horvitz, Henry Kautz
Computerized generation of humor is a notoriously difficult AI problem.
no code implementations • 10 Mar 2016 • Nabil Hossain, Tianran Hu, Roghayeh Feizi, Ann Marie White, Jiebo Luo, Henry Kautz
Nearly all previous work on geo-locating latent states and activities from social media confounds general discussions about activities, self-reports of users participating in those activities at times in the past or future, and self-reports made at the immediate time and place the activity occurs.