Conference Paper

Experiments with Interactive Question-Answering.

DOI: 10.3115/1219840.1219866 Conference: ACL 2005, 43rd Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, 25-30 June 2005, University of Michigan, USA
Source: DBLP

ABSTRACT This paper describes a novel framework for interactive question-answering (Q/A) based on predictive questioning. Gen- erated off-line from topic representations of complex scenarios, predictive ques- tions represent requests for information that capture the most salient (and diverse) aspects of a topic. We present experimen- tal results from large user studies (featur- ing a fully-implemented interactive Q/A system named FERRET) that demonstrates that surprising performance is achieved by integrating predictive questions into the context of a Q/A dialogue.

  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a supervised approach for automatically learning good decompositions of complex questions. The training data generation phase mainly builds on three steps to produce a list of simple questions corresponding to a complex question: i) the extraction of the most important sentences from a given set of relevant documents (which contains the answer to the complex question), ii) the simplification of the extracted sentences, and iii) their transformation into questions containing candidate answer terms. Such questions, considered as candidate decompositions, are manually annotated (as good or bad candidates) and used to train a Support Vector Machine (SVM) classifier. Experiments on the DUC data sets prove the effectiveness of our approach.
    Proceedings of the 17th international conference on Applications of Natural Language Processing and Information Systems; 06/2012
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we describe how Lan-guage Computer Corporation's GISTEX-TER question-directed summarization sys-tem combines multiple strategies for ques-tion decomposition and summary genera-tion in order to produce summary-length answers to complex questions. In addi-tion, we introduce a novel framework for question-directed summarization that uses a state-of-the-art textual entailment sys-tem (Hickl et al., 2006) in order to se-lect a single responsive summary answer from amongst a number of candidate sum-maries. We show that by considering en-tailment relationships between sentences extracted for a summary, we can automati-cally create semantic "Pyramids" that can be used to identify answer passages that are both relevant and responsive.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Today, automatic generation of questions is a considerable problem by many researchers. Automatic question generation from text has two major activity domains: dialogue/interactive question answering systems and educational assessment. In this paper, a proposed system is designed, implemented and tested to automate question generation process. The proposed system generates questions by selecting one sentence at a time, extracts sections of the source sentence, then applies transformation rules or patterns for constructing a question. It uses pure syntactic pattern-matching approach to generate content-related questions in order to improve the independent study of any textual material. The proposed system is powered by OpenNLP open source statistical parser to generate the questions using pattern matching strategy. The system is able to learn dynamically, ready to use in ease manner and accepts large-scale number of rules.


Available from