Context modeling for IQA: the role of tasks and entities

Authors:
Raffaella Bernardi;Manuel Kirschner
Affiliations:
Free University of Bozen-Bolzano, Italy;Free University of Bozen-Bolzano, Italy
Venue:
KRAQ '08 Coling 2008: Proceedings of the workshop on Knowledge and Reasoning for Answering Questions
Year:
2008

Citing 5
Cited 0

The representation and use of focus in dialogue understanding.

The representation and use of focus in dialogue understanding.
User-system dialogues and the notion of focus

The Knowledge Engineering Review
The Proposition Bank: An Annotated Corpus of Semantic Roles

Computational Linguistics
Follow-up question handling in the imix and ritel systems: A comparative study

Natural Language Engineering
Contextual phenomena and thematic relations in database QA dialogues: results from a Wizard-of-Oz experiment

IQA '06 Proceedings of the Interactive Question Answering Workshop at HLT-NAACL 2006

Quantified Score

Hi-index	0.00

Visualization

Abstract

In a realistic Interactive Question Answering (IQA) setting, users frequently ask follow-up questions. By modeling how the questions' focus evolves in IQA dialogues, we want to describe what makes a particular follow-up question salient. We introduce a new focus model, and describe an implementation of an IQA system that we use for exploring our theory. To learn properties of salient focus transitions from data, we use logistic regression models that we validate on the basis of predicted answer correctness.