The role of context in question answering systems

By Jimmy J. Lin, Dennis Quan, Vineet Sinha, Karun Bakshi, David Huynh, Boris Katz, David R Karger. 2003

73 citations recorded by the source corpus.

Despite recent advances in natural language question an-swering technology, the problem of designing effective user interfaces has been largely unexplored. We conducted a user study to investigate the problem and discovered that overall, users prefer a paragraph-sized chunk of text over just an exact phrase as the answer to their questions. Fur-thermore, users generally prefer answers embedded in con-text, regardless of the perceived reliability of the source documents. When users research a topic, increasing the amount of text returned to users significantly decreases the number of queries that they pose to the system, suggesting that users utilize supporting text to answer related ques-tions. We believe that these results can serve to guide future developments in question answering user interfaces.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing

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. Jimmy J. Lin
2. Wei Yang
3. Zeynep Akkalyoncu Yilmaz
4. Luchen Tan
5. Ming Li
6. Yuqing Xie
7. Kun Xiong
8. Jaime Teevan

In Information Systems

1. Wei Yang
2. Jimmy J. Lin
3. Jaime Teevan
4. Luchen Tan
5. Ming Li
6. Yuqing Xie
7. Kun Xiong
8. Edward Cutrell

In Natural Language Processing

1. Wei Yang
2. Luchen Tan
3. Jaime Teevan
4. Jimmy J. Lin
5. David R Karger
6. Ming Li
7. Yuqing Xie
8. Kun Xiong

Citations in the corpus

• End-to-End Open-Domain Question Answering with BERTserini (2019, background): “The answer span is highlighted in the response (Lin et al., 2003).”
• What are you looking for?: an eye-tracking study of information usage in web search (2007, background): “Previous work in question-answering suggests that providing additional textual context with answers substantially boosts user preference and performance [16].”
• The perfect search engine is not enough: a study of orienteering behavior in directed search (2004, background): “Attempts to build such a search engine have focused on improving on keyword search by permitting users to better specify their information need through meta-data [28], natural language [15], and even context [14].”