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.

0 Followers
 · 
98 Views
  • 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.
  • [Show abstract] [Hide abstract]
    ABSTRACT: We use extractive multi-document summarization techniques to perform complex question answering and formulate it as a reinforcement learning problem. Given a set of complex questions, a list of relevant documents per question, and the corresponding human generated summaries (i.e. answers to the questions) as training data, the reinforcement learning module iteratively learns a number of feature weights in order to facilitate the automatic generation of summaries i.e. answers to previously unseen complex questions. A reward function is used to measure the similarities between the candidate (machine generated) summary sentences and the abstract summaries. In the training stage, the learner iteratively selects the important document sentences to be included in the candidate summary, analyzes the reward function and updates the related feature weights accordingly. The final weights are used to generate summaries as answers to unseen complex questions in the testing stage. Evaluation results show the effectiveness of our system. We also incorporate user interaction into the reinforcement learner to guide the candidate summary sentence selection process. Experiments reveal the positive impact of the user interaction component on the reinforcement learning framework.
    Information Processing & Management 05/2015; 51(3). DOI:10.1016/j.ipm.2015.01.002 · 1.07 Impact Factor
  • 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.

Preview

Download
0 Downloads
Available from