In recent years, conversational agents have provided a natural and convenient access to useful information in people’s daily life . The main challenge is how to well capture and fullyexplore the historical context in conversation to facilitate effectivelarge-scale retrieval . We propose a novel graph-guided retrieval method to model the relations amonganswers across conversation turns . We also propose to incorporate the multi-roundrelevance feedback technique to explore the impact of the retrieval context on current question understanding. Experimental results on the public datasetverify the effectiveness of our proposed method . Notably, the F1 score is improved by 5% and 11% with predicted history answers and true history answers, respectively . The F1 scores are improved by . 5% by . 11% and with predicted histories answers andtrue history answers,. respectively, respectively. We propose to use a novel method to retrieve more relevant passages for subsequent answers, and to incorporate a multi-rotrotrotting technique to examine the use of the . proposed method. The method is used in the public datasetsverify .

Author(s) : Yongqi Li, Wenjie Li, Liqiang Nie

Links : PDF - Abstract

Code :
Coursera

Keywords : method - answers - retrieval - history - multi -

Leave a Reply

Your email address will not be published. Required fields are marked *