Paper: Exploring Topic Continuation Follow-up Questions using Machine Learning

ACL ID N09-3003
Title Exploring Topic Continuation Follow-up Questions using Machine Learning
Venue HLT-NAACL Companion Volume: Student Research Workshop and Doctoral Consortium
Session
Year 2009
Authors

Some of the Follow-Up Questions (FU Q) that an Interactive Question Answering (IQA) sys- tem receives are not topic shifts, but rather continuations of the previous topic. In this pa- per, we propose an empirical framework to ex- plore such questions, with two related goals in mind: (1) modeling the different relations that hold between the FU Q’s answer and either the FU Q or the preceding dialogue, and (2) show- ing how this model can be used to identify the correct answer among several answer candi- dates. For both cases, we use Logistic Regres- sion Models that we learn from real IQA data collected through a live system. We show that by adding dialogue context features and fea- tures based on sequences of domain-specific actions that represent the questions and an- swers, we obtain i...