Generating Question-Answer Hierarchies

Kalpesh Krishna, Mohit Iyyer


Abstract
The process of knowledge acquisition can be viewed as a question-answer game between a student and a teacher in which the student typically starts by asking broad, open-ended questions before drilling down into specifics (Hintikka, 1981; Hakkarainen and Sintonen, 2002). This pedagogical perspective motivates a new way of representing documents. In this paper, we present SQUASH (Specificity-controlled Question-Answer Hierarchies), a novel and challenging text generation task that converts an input document into a hierarchy of question-answer pairs. Users can click on high-level questions (e.g., “Why did Frodo leave the Fellowship?”) to reveal related but more specific questions (e.g., “Who did Frodo leave with?”). Using a question taxonomy loosely based on Lehnert (1978), we classify questions in existing reading comprehension datasets as either GENERAL or SPECIFIC . We then use these labels as input to a pipelined system centered around a conditional neural language model. We extensively evaluate the quality of the generated QA hierarchies through crowdsourced experiments and report strong empirical results.
Anthology ID:
P19-1224
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2321–2334
Language:
URL:
https://aclanthology.org/P19-1224
DOI:
10.18653/v1/P19-1224
Bibkey:
Cite (ACL):
Kalpesh Krishna and Mohit Iyyer. 2019. Generating Question-Answer Hierarchies. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2321–2334, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Generating Question-Answer Hierarchies (Krishna & Iyyer, ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1224.pdf
Poster:
 P19-1224.Poster.pdf
Note:
 P19-1224.Note.pdf
Code
 additional community code
Data
CoQAQuACSQuAD