DMCA
Implementing clarification dialogues in open domain question answering (2005)
| Venue: | Journal of Natural Language Engineering |
| Citations: | 9 - 1 self |
BibTeX
@ARTICLE{Boni05implementingclarification,
author = {Marco De Boni and Suresh Manandhar},
title = {Implementing clarification dialogues in open domain question answering},
journal = {Journal of Natural Language Engineering},
year = {2005},
volume = {1},
pages = {1--7}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We examine the implementation of clarification dialogues, a mechanism for ensuring that question answering systems take into account user goals by allowing them to ask series of related questions either by refining or expanding on previous questions with follow-up questions, in the context of open domain Question Answering systems. We develop an algorithm for clarification dialogue rec-ognition through the analysis of collected data on clarification dialogues and examine the impor-tance of clarification dialogue recognition for question answering. The algorithm is evaluated and shown to successfully recognize the start and continuation of clarification dialogues in 94 % of cases. We then show the usefulness of the algorithm by demonstrating how the recognition of clari-fication dialogues can simplify the task of answer retrieval. 1 Clarification dialogues in Question Answering Open domain Question Answering (QA) Systems, as defined for example in the TREC evaluation framework which currently provides a widely accepted standard baseline for research in this area (see Voorhees 2002 for an outline of the framework and an overview of current systems), aim to determine an answer to a question (which is not limited to a particular task or topic) by searching for a response in a collection of documents such as newspaper articles. In order to achieve this (see
Keyphrases
clarification dialogue open domain question standard baseline follow-up question clari-fication dialogue clarification dialogue rec-ognition particular task open domain question answering system clarification dialogue recognition current system related question trec evaluation framework answer retrieval previous question account user goal question answering newspaper article
