Connecting question answering and conversational agents: Contextualizing German questions for interactive question answering systems

Waltinger U, Breuing A, Wachsmuth I (2012)
KI - Künstliche Intelligenz 26(4): 381-390.

Zeitschriftenaufsatz | Veröffentlicht | Englisch
 
Download
OA
Abstract / Bemerkung
Research results in the field of Question Answering (QA) have shown that the classification of natural language questions significantly contributes to the accuracy of the generated answers. In this paper we present an approach which extends the prevalent question classification techniques by additionally considering further contextual information provided by the questions. Thereby we focus on improving the conversational abilities of existing interactive interfaces by enhancing their underlying QA systems in terms of response time and correctness. As a result, we are able to introduce a method based on a tripartite contextualization. First, we present a comprehensive question classification experiment based on machine learning using two different datasets and various feature sets for the German language. Second, we propose a method for detecting the focus chunk of a given question, that is, for identifying which part of the question is fundamentally relevant to the answer and which part refers to a specification of it. Third, we investigate how to identify and label the topic of a given question by means of a human-judgment experiment. We show that the resulting contextualization method contributes to an improvement of existing question answering systems and enhances their application within interactive scenarios.
Stichworte
interactive question answering; question classification; topic spotting; machine learning
Erscheinungsjahr
2012
Zeitschriftentitel
KI - Künstliche Intelligenz
Band
26
Ausgabe
4
Seite(n)
381-390
ISSN
0933-1875
eISSN
1610-1987
Page URI
https://pub.uni-bielefeld.de/record/2498074

Zitieren

Waltinger U, Breuing A, Wachsmuth I. Connecting question answering and conversational agents: Contextualizing German questions for interactive question answering systems. KI - Künstliche Intelligenz. 2012;26(4):381-390.
Waltinger, U., Breuing, A., & Wachsmuth, I. (2012). Connecting question answering and conversational agents: Contextualizing German questions for interactive question answering systems. KI - Künstliche Intelligenz, 26(4), 381-390. doi:10.1007/s13218-012-0208-1
Waltinger, Ulli, Breuing, Alexa, and Wachsmuth, Ipke. 2012. “Connecting question answering and conversational agents: Contextualizing German questions for interactive question answering systems”. KI - Künstliche Intelligenz 26 (4): 381-390.
Waltinger, U., Breuing, A., and Wachsmuth, I. (2012). Connecting question answering and conversational agents: Contextualizing German questions for interactive question answering systems. KI - Künstliche Intelligenz 26, 381-390.
Waltinger, U., Breuing, A., & Wachsmuth, I., 2012. Connecting question answering and conversational agents: Contextualizing German questions for interactive question answering systems. KI - Künstliche Intelligenz, 26(4), p 381-390.
U. Waltinger, A. Breuing, and I. Wachsmuth, “Connecting question answering and conversational agents: Contextualizing German questions for interactive question answering systems”, KI - Künstliche Intelligenz, vol. 26, 2012, pp. 381-390.
Waltinger, U., Breuing, A., Wachsmuth, I.: Connecting question answering and conversational agents: Contextualizing German questions for interactive question answering systems. KI - Künstliche Intelligenz. 26, 381-390 (2012).
Waltinger, Ulli, Breuing, Alexa, and Wachsmuth, Ipke. “Connecting question answering and conversational agents: Contextualizing German questions for interactive question answering systems”. KI - Künstliche Intelligenz 26.4 (2012): 381-390.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
Dieses Objekt ist durch das Urheberrecht und/oder verwandte Schutzrechte geschützt. [...]
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-09-06T09:18:03Z
MD5 Prüfsumme
00cf6d173f67bb8e6ebcfc0ee8e9a46d


Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar