UZH-Logo

Maintenance Infos

The importance of how-questions in technical domains


Schwitter, R; Rinaldi, F; Clematide, S (2004). The importance of how-questions in technical domains. In: Proc of the Question-Answering workshop of TALN 04, Fez, Morocco, April 2004 - April 2004, 451-460.

Abstract

How-questions are difficult to answer automatically, since the answers are usually not available in form of a single string in a technical document but need to be constructed from various information located at different places in the document or even from external knowledge sources.
In this paper, we show how procedural questions can be answered in the context of ExtrAns.
ExtrAns is an answer extraction system and operates over technical documentations that are rich in procedural knowledge. This procedural knowledge is often expressed in a procedural writing style that follows more or less strict guidelines. These guidelines together with typographical
conventions can be exploited in a systematic way to first construct and then extract informative answers to procedural questions.

How-questions are difficult to answer automatically, since the answers are usually not available in form of a single string in a technical document but need to be constructed from various information located at different places in the document or even from external knowledge sources.
In this paper, we show how procedural questions can be answered in the context of ExtrAns.
ExtrAns is an answer extraction system and operates over technical documentations that are rich in procedural knowledge. This procedural knowledge is often expressed in a procedural writing style that follows more or less strict guidelines. These guidelines together with typographical
conventions can be exploited in a systematic way to first construct and then extract informative answers to procedural questions.

Downloads

71 downloads since deposited on 06 Aug 2009
13 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Language:English
Event End Date:April 2004
Deposited On:06 Aug 2009 12:47
Last Modified:05 Apr 2016 13:15
Permanent URL: https://doi.org/10.5167/uzh-19115

Download

[img]
Preview
Filetype: PDF
Size: 214kB

TrendTerms

TrendTerms displays relevant terms of the abstract of this publication and related documents on a map. The terms and their relations were extracted from ZORA using word statistics. Their timelines are taken from ZORA as well. The bubble size of a term is proportional to the number of documents where the term occurs. Red, orange, yellow and green colors are used for terms that occur in the current document; red indicates high interlinkedness of a term with other terms, orange, yellow and green decreasing interlinkedness. Blue is used for terms that have a relation with the terms in this document, but occur in other documents.
You can navigate and zoom the map. Mouse-hovering a term displays its timeline, clicking it yields the associated documents.

Author Collaborations