Empirical studies of discourse representations for natural language interfaces
EACL '89 Proceedings of the fourth conference on European chapter of the Association for Computational Linguistics
Follow-up question handling in the imix and ritel systems: A comparative study
Natural Language Engineering
IQA '06 Proceedings of the Interactive Question Answering Workshop at HLT-NAACL 2006
A data driven approach to relevancy recognition for contextual question answering
IQA '06 Proceedings of the Interactive Question Answering Workshop at HLT-NAACL 2006
Hi-index | 0.00 |
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.