TY - GEN
T1 - User intent prediction in information-seeking conversations
AU - Qu, Chen
AU - Zhang, Yongfeng
AU - Yang, Liu
AU - Trippas, Johanne R.
AU - Bruce Croft, W.
AU - Qiu, Minghui
N1 - Publisher Copyright:
© 2019 Association for Computing Machinery.
PY - 2019/3/8
Y1 - 2019/3/8
N2 - Conversational assistants are being progressively adopted by the general population. However, they are not capable of handling complicated information-seeking tasks that involve multiple turns of information exchange. Due to the limited communication bandwidth in conversational search, it is important for conversational assistants to accurately detect and predict user intent in information-seeking conversations. In this paper, we investigate two aspects of user intent prediction in an information-seeking setting. First, we extract features based on the content, structural, and sentiment characteristics of a given utterance, and use classic machine learning methods to perform user intent prediction. We then conduct an in-depth feature importance analysis to identify key features in this prediction task. We find that structural features contribute most to the prediction performance. Given this finding, we construct neural classifiers to incorporate context information and achieve better performance without feature engineering. Our findings can provide insights into the important factors and effective methods of user intent prediction in information-seeking conversations.
AB - Conversational assistants are being progressively adopted by the general population. However, they are not capable of handling complicated information-seeking tasks that involve multiple turns of information exchange. Due to the limited communication bandwidth in conversational search, it is important for conversational assistants to accurately detect and predict user intent in information-seeking conversations. In this paper, we investigate two aspects of user intent prediction in an information-seeking setting. First, we extract features based on the content, structural, and sentiment characteristics of a given utterance, and use classic machine learning methods to perform user intent prediction. We then conduct an in-depth feature importance analysis to identify key features in this prediction task. We find that structural features contribute most to the prediction performance. Given this finding, we construct neural classifiers to incorporate context information and achieve better performance without feature engineering. Our findings can provide insights into the important factors and effective methods of user intent prediction in information-seeking conversations.
KW - Conversational search
KW - Information-seeking conversations
KW - Multi-turn question answering
KW - User intent prediction
UR - http://www.scopus.com/inward/record.url?scp=85063141744&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85063141744&partnerID=8YFLogxK
U2 - 10.1145/3295750.3298924
DO - 10.1145/3295750.3298924
M3 - Conference contribution
AN - SCOPUS:85063141744
T3 - CHIIR 2019 - Proceedings of the 2019 Conference on Human Information Interaction and Retrieval
SP - 25
EP - 33
BT - CHIIR 2019 - Proceedings of the 2019 Conference on Human Information Interaction and Retrieval
PB - Association for Computing Machinery, Inc
T2 - 4th ACM SIGIR Conference on Information Interaction and Retrieval, CHIIR 2019
Y2 - 10 March 2019 through 14 March 2019
ER -