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.

Context Modeling for IQA: The Role of Tasks and Entities

Bernardi, Raffaella;
2008-01-01

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.
2008
Coling 2008: Proceedings of the workshop on Knowledge and Reasoning for Answering Questions
Manchester, UK
Coling 2008
Bernardi, Raffaella; M., Kirschner
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/93308
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
  • OpenAlex ND
social impact