Answer Interaction in Non-factoid Question Answering Systems
arXiv:1901.03491 · doi:10.1145/3295750.3298946
Abstract
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.
Accepted to CHIIR 2019
References in corpus (4)
- Deep Learning for Answer Sentence Selection
- Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems
- Analyzing and Characterizing User Intent in Information-seeking Conversations
- aNMM: Ranking Short Answer Texts with Attention-Based Neural Matching Model
Cited by in corpus (5)
- Open-Retrieval Conversational Question Answering
- Attentive History Selection for Conversational Question Answering
- Towards a Better Understanding Human Reading Comprehension with Brain Signals
- Explaining Predictions from Tree-based Boosting Ensembles
- Towards an Atlas of Cultural Commonsense for Machine Reasoning