Exploring Topic Continuation Follow-up Questions using Machine Learning

Some of the Follow-Up Questions (FU Q) that an Interactive Question Answering (IQA) system receives are not topic shifts, but rather continuations of the previous topic. In this paper, we propose an empirical framework to explore 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) showing how this model can be used to identify the correct answer among several answer candidates. For both cases, we use Logistic Regression Models that we learn from real IQA data collected through a live system. We show that by adding dialogue context features and features based on sequences of domain-specific actions that represent the questions and answers, we obtain important additional predictors for the model, and improve the accuracy with which our system finds correct answers.