TY - GEN
T1 - CONSISTENT
T2 - 2022 Findings of the Association for Computational Linguistics: EMNLP 2022
AU - Chakrabarty, Tuhin
AU - Lewis, Justin
AU - Muresan, Smaranda
N1 - Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022
Y1 - 2022
N2 - Recent work on question generation has largely focused on factoid questions such as who, what, where, when about basic facts. Generating open-ended why, how, what, etc. questions that require long-form answers have proven more difficult. To facilitate the generation of open-ended questions, we propose CONSISTENT, a new end-to-end system for generating open-ended questions that are answerable from and faithful to the input text. Using news articles as a trustworthy foundation for experimentation, we demonstrate our model's strength over several baselines using both automatic and human-based evaluations. We contribute an evaluation dataset of expert-generated open-ended questions.We discuss potential downstream applications for news media organizations.
AB - Recent work on question generation has largely focused on factoid questions such as who, what, where, when about basic facts. Generating open-ended why, how, what, etc. questions that require long-form answers have proven more difficult. To facilitate the generation of open-ended questions, we propose CONSISTENT, a new end-to-end system for generating open-ended questions that are answerable from and faithful to the input text. Using news articles as a trustworthy foundation for experimentation, we demonstrate our model's strength over several baselines using both automatic and human-based evaluations. We contribute an evaluation dataset of expert-generated open-ended questions.We discuss potential downstream applications for news media organizations.
UR - https://www.scopus.com/pages/publications/85149867465
U2 - 10.18653/v1/2022.findings-emnlp.283
DO - 10.18653/v1/2022.findings-emnlp.283
M3 - Conference contribution
AN - SCOPUS:85149867465
T3 - Findings of the Association for Computational Linguistics: EMNLP 2022
SP - 6983
EP - 6997
BT - Findings of the Association for Computational Linguistics
A2 - Goldberg, Yoav
A2 - Kozareva, Zornitsa
A2 - Zhang, Yue
PB - Association for Computational Linguistics (ACL)
Y2 - 7 December 2022 through 11 December 2022
ER -