Learning to Re-rank for Interactive Problem Resolution and Query Refinement
Rashmi Gangadharaiah, Balakrishnan Narayanaswamy, Charles Elkan · 2014
We study the design of an information re-trieval (IR) system that assists customer service agents while they interact with end-users. The type of IR needed is difficult because of the large lexical gap between problems as described by cus-tomers, and solutions. We describe an approach that bridges this lexical gap by learning semantic relatedness using tensor representations. Queries that are short and vague, which are common in practice, re-sult in a large number of documents be-ing retrieved, and a high cognitive load for customer service agents. We show how to reduce this burden by providing suggestions that are selected based on the learned measures of semantic relatedness. Experiments show that the approach offers substantial benefit compared to the use of standard lexical similarity. 1