The Process of Question Answering -- A Computer Simulation of Cognition
Open accessAbstract
The processes of question answering are not a very well documented area of human intellectual activity, although our daily life is pervaded with it. According to Wendy Lehnert in a recent study on this subject this lack of insight is due to the fact that People are largely unconscious of the cognitive processes involved in answering a question, and are consequently insensitive to the complexities of those processes. But this may be true for almost any psychological activity. The maining of questions and their appropriate answers has been felt intuitively by cognitive scientist (and their predecessors) to be a conceptual swamp. Questions can be used for almost any purpose in communication: not only to obtain information or to request actions, but also to induce information (as in a Socratic dialogue, of. Collins, 1977), to change topic in a conversation and even to answer questions. One may therefore wonder whether questions form a proper conceptual category. The interpretation of a question may cover the complete area of discourse comprehension. But the production of an answer may involve even more: it may elicit any form of human cognitive processing. And, then, the truth value or appropriateness of the answer can be the subject of philosophic debate. Although Wendy Lehnert has put in her study some important restrictions to the nature of questions and to the conceptual domain they refer to (stories), she has by no means evaded the complexity
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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 [97]
Cites
Lea, W. A. (1980) · Prentice Hall PTR eBooks · Cited by 482 · see citing works
Review of the ARPA Speech Understanding Project
Klatt, D. H. (1977) · The Journal of the Acoustical Society of America · doi:10.1121/1.381666 · Cited by 178 · see citing works
On primitives, prototypes, and other semantic anomalies
Winograd, T. (1978) · doi:10.3115/980262.980267 · Cited by 29 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Explanations From Intelligent Systems: Theoretical Foundations and Implications for Practice1
Gregor, S., & Benbasat, I. (1999) · MIS Quarterly · doi:10.2307/249487 · Cited by 535 · see citing works
Mulla, N., & Gharpure, P. (2023) · Progress in Artificial Intelligence · doi:10.1007/s13748-023-00295-9 · Cited by 132 · see citing works
Automatic coding of dialogue acts in collaboration protocols
Erkens, G., & Janssen, J. (2008) · International Journal of Computer-Supported Collaborative Learning · doi:10.1007/s11412-008-9052-6 · Cited by 103 · see citing works
- Authors
- Colclough, M., & Lehnert, W. G.
- Venue
- The Journal of the Operational Research Society
- Publisher
- JSTOR
- Published
- 1979-08
- Volume
- 30
- Issue
- 8
- Pages
- 770
- ISSN
- 0160-5682 (ISSN-L)
- OpenAlex
- W1966542308
- Cited by
- 98
- References
- 3
- Citations by year
- 2023: 2 · 2021: 2 · 2020: 2 · 2019: 1 · 2018: 4 · 2017: 2 · 2015: 3 · 2014: 4 · 2013: 4 · 2012: 4
- FWCI
- 4.06
- Type
- journal article
- Language
- en
- Open access
- green
- www.aclweb.org
- Licence
- cc-by-nc-sa
- Locations
- Journal of the Operational Research Society (publishedVersion)
- OLAC - Open Language Archives Community (submittedVersion)
- Americanae (AECID Library) (submittedVersion, cc-by-nc-sa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Logic, Reasoning, and Knowledge
- Social Sciences › Arts and Humanities › Language and Linguistics › Syntax, Semantics, Linguistic Variation
- Keywords
- question answering, cognitive processes, question comprehension, discourse comprehension, Socratic dialogue, conversation
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