Answer Interaction in Non-factoid Question Answering Systems

By Chen Qu, Liu Yang, W. Bruce Croft, Falk Scholer, Yongfeng Zhang. 2019

24 citations recorded by the source corpus.

Information retrieval systems are evolving from document retrieval to answer retrieval. Web search logs provide large amounts of data about how people interact with ranked lists of documents, but very little is known about interaction with answer texts. In this paper, we use Amazon Mechanical Turk to investigate three answer presentation and interaction approaches in a non-factoid question answering setting. We find that people perceive and react to good and bad answers very differently, and can identify good answers relatively quickly. Our results provide the basis for further investigation of effective answer interaction and feedback methods.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. W. Bruce Croft
2. Liu Yang
3. Maarten de Rijke
4. Chen Qu
5. Hamed Zamani
6. Minghui Qiu
7. Mohit Iyyer
8. Cen Chen

In Information Systems

1. Liu Yang
2. W. Bruce Croft
3. Maarten de Rijke
4. Chen Qu
5. Minghui Qiu
6. Mohit Iyyer
7. Hamed Zamani
8. Jamie Callan

Citations in the corpus

• Explaining Predictions from Tree-based Boosting Ensembles (2019, background): “This can be in the context of rankings [10], recommendations [11], or digital assistants that engage in interactive question answering [7].”
• Open-Retrieval Conversational Question Answering (2020, background): “Another rich body of work targets the user-oriented aspect [7, 30, 31, 40–43] for conversational information seeking.”