Generating Question-Answer Hierarchies
Open accessAbstract
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.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In [98], question classification based on Lehnert's classification is used to tag questions and then in a conditional neural network model.
“An approach using question classification based on Lehnert’s classification [97] is used to tag questions and later on used in a conditional neural network-based model in [98].”
From Automatic question generation: a review of methodologies, datasets, evaluation metrics, and applications (2023) · cites this paper as [98]
[98] introduces SQUASH, a task that converts text into a hierarchy of question-answer sets from broad high-level questions to more refined questions.
“The authors introduce a new task called SQUASH (Specificity-controlled Question Answer Hierarchies) which converts the text into a hierarchy consisting of question–answer sets which start at broader “high-level” questions and keep proceeding with more refined questions down the hierarchy.”
From Automatic question generation: a review of methodologies, datasets, evaluation metrics, and applications (2023) · cites this paper as [98]
The [98] pipeline was tested on SQuAD, QuAC, and CoQA and produced promising results.
“The authors test their proposed pipeline on the 3 datasets (SQuAD, QuAC, CoQA) and get promising results.”
From Automatic question generation: a review of methodologies, datasets, evaluation metrics, and applications (2023) · cites this paper as [98]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 53 · Cited by 44
Research works printed but not linked: 6
- Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Ben- gio. 2015. Neural machine translation by jointly learning to align and translate. In Proc. Inter- national Conference on Learning Representations (ICLR).
- Angela Fan, Mike Lewis, and Yann Dauphin. 2018. Hi- erarchical neural story generation. In Proc. Associ- ation for Computational Linguistics (ACL).
- Jaakko Hintikka. 1981. The logic of information- seeking dialogues: A model. Werner Becker and Wilhelm K. Essler Konzepte der Dialektik, pages 212-231.
- Matthew Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word rep- resentations. In Proc. Conference of the North American Chapter of the Association for Computa- tional Linguistics -Human Language Technologies (NAACL HLT).
- Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. Neural machine translation of rare words with subword units. In Proc. Association for Computa- tional Linguistics (ACL).
- Amy X. Zhang, Lea Verou, and David Karger. 2017. Wikum: Bridging discussion forums and wikis using recursive summarization. In Conference on Com- puter Supported Cooperative Work and Social Com- puting (CSCW).
- Authors
- Krishna, K., & Iyyer, M.
- Affiliations
- University of Massachusetts Amherst (US)
- Venue
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Published
- 2019
- Pages
- 2321-2334
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W2948913516
- Cited by
- 44
- References
- 53
- Citations by year
- 2026: 2 · 2025: 2 · 2024: 4 · 2023: 10 · 2022: 8 · 2021: 11 · 2020: 7
- FWCI
- 2.49
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Allen Institute for Artificial Intelligence
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- squash, question generation, document representation, question taxonomy, knowledge acquisition
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
