Learning question classifiers
Published 1 January 2002
Xin Li, Dan Roth
Citations1,276
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A hierarchical classifier is learned that is guided by a layered semantic hierarchy of answer types, and eventually classifies questions into fine-grained classes.
Abstract
In order to respond correctly to a free form factual question given a large collection of texts, one needs to understand the question to a level that allows determining some of the constraints the question imposes on a possible answer. These constraints may include a semantic classification of the sought after answer and may even suggest using different strategies when looking for and verifying a candidate answer. This paper
Keywords
Computer Science
Studies in linguistics and philosophyParsing By Chunks
878 Citations1991Steven Abney
The typical chunk consists of a single content word surrounded by a constellation of function words, matching a fixed template, and the relationships between chunks are mediated more by lexical selection than by rigid templates.
Machine LearningA Winnow-Based Approach to Context-Sensitive Spelling Correction
282 Citations1999Andrew R. Golding, Dan Roth
This work presents an algorithm combining variants of Winnow and weighted-majority voting, and applies it to a problem in the aforementioned class: context-sensitive spelling correction, and finds that WinSpell achieves accuracies significantly higher than BaySpell was able to achieve in either the pruned or unpruned condition.
FALCON: Boosting Knowledge for Answer Engines
249 Citations2000Sanda M. Harabagiu, Dan Moldovan +7 more
FALCON, an answer engine that integrates different forms of syntactic, semantic and pragmatic knowledge for the goal of achieving better performance is discussed.
Deep Read
219 Citations1999Lynette Hirschman, Marc Light +2 more
Initial work on Deep Read, an automated reading comprehension system that accepts arbitrary text input (a story) and answers questions about it is described, with a baseline system that retrieves the sentence containing the answer 30--40% of the time.
Toward semantics-based answer pinpointing
182 Citations2001Eduard Hovy, Laurie Gerber +3 more
The treatment of questions (Question-Answer Typology, question parsing, and results) in the Weblcopedia question answering system are described.
arXiv (Cornell University)Learning to Resolve Natural Language Ambiguities: A Unified Approach
175 Citations1998Dan Roth
An extensive experimental comparison of the approach with other methods on several well studied lexical disambiguation tasks such as context-sensitive spelling correction, prepositional phrase attachment and part of speech tagging shows that it outperforms other methods tried for these tasks or performs comparably to the best.
Parsing and question classification for question answering
150 Citations2001Ulf Hermjakob
It is demonstrated that for this type of application, parse trees have to be semantically richer and structurally more oriented towards semantics than what most treebanks offer.
Kluwer Academic Publishers eBooksPrinciple-Based Parsing: Computation and Psycholinguistics
150 Citations1991Steven Abney, Robert C. Berwick +1 more
Principles of principle-based parsing, R.C. Berwick deductive parsing - the use of knowledge of language, M.S. Stabler Jr parsing with changing grammars - evaluating a language acquisition model, and the computational implementation of Principle-based parsers.
Natural Language EngineeringAnalyses for elucidating current question answering technology
88 Citations2001Marc Light, Gideon Mann +2 more
This paper takes a detailed look at the performance of components of an idealized question answering system on two different tasks: the TREC Question Answering task and a set of reading comprehension exams.
Relational learning via propositional algorithms: an information extraction case study
86 Citations2001Dan Roth, Wen-tau Yih
This paper develops a new paradigm for relational learning which allows for the representation and learning of relational information using propositional means and allows the use of any propositional algorithm, including probabilistic algorithms, within it.
Exploring evidence for shallow parsing
68 Citations2001Xin Li, Dan Roth
It is concluded that directly learning to perform these tasks as shallow parsers do is advantageous over full parsers both in terms of performance and robustness to new and lower quality texts.
International Joint Conference on Artificial IntelligenceA conceptual theory of question answering
52 Citations1986Wendy G. Lehnert
A theory of Q/A has been proposed from the perspective of natural language processing that relies on ideas in conceptual information processing and theories of human memory organization and this theory has been implemented in a computer program, QUALM.
A Sequential Model for Multi-Class Classification
38 Citations2001Yair Even-Zohar, Dan Roth
A sequential learning model is suggested that utilizes classifiers to sequentially restrict the number of competing classes while maintaining, with high probability, the presence of the true outcome in the candidates set.
Relational Representations that Facilitate Learning
22 Citations1999Chad Cumby, Dan Roth
This work develops an expressive relational representation language that allows the use of propositional learning algorithms when learning relational definitions and serves as an intermediate level between a raw description of observations in the world and a propositional learning system that attempts to learn definitions for concepts and relations.
Learning Components for A Question-Answering System.
7 Citations2001Dan Roth, Gio Kao Kao +7 more
A unified learning approach is used to develop a part-of-speech tagger, a shallow parser, a named entity recognizer and a module for identifying a question's target.