skip to main content

Title: Weighted network search games with multiple hidden objects and multiple search teams
Authors:
;
Award ID(s):
1901721
Publication Date:
NSF-PAR ID:
10180819
Journal Name:
European Journal of Operational Research
ISSN:
0377-2217
Sponsoring Org:
National Science Foundation
More Like this
  1. Asking clarifying questions in response to ambiguous or faceted queries has been recognized as a useful technique for various information retrieval systems, in particular, conversational search systems with limited bandwidth interfaces. Analyzing and generating clarifying question have been recently studied in the literature. However, accurate utilization of user responses to clarifying questions has been relatively less explored. In this paper, we propose a neural network model based on a novel attention mechanism, called multi source attention network. Our model learns a representation for a user-system conversation that includes clarifying questions. In more detail, with the help of multiple information sources, our model weights each term in the conversation. In our experiments, we use two separate external sources, including the top retrieved documents and a set of different possible clarifying questions for the query. We implement the proposed representation learning model for two downstream tasks in conversational search; document retrieval and next clarifying question selection. We evaluate our models using a public dataset for search clarification. Our experiments demonstrate significant improvements compared to competitive baselines.