AmbigQA: Answering Ambiguous Open-domain Questions

@inproceedings{Min2020AmbigQAAA,
  title={AmbigQA: Answering Ambiguous Open-domain Questions},
  author={Sewon Min and Julian Michael and Hannaneh Hajishirzi and Luke Zettlemoyer},
  booktitle={EMNLP},
  year={2020}
}
Ambiguity is inherent to open-domain question answering; especially when exploring new topics, it can be difficult to ask questions that have a single, unambiguous answer. In this paper, we introduce AmbigQA, a new open-domain question answering task which involves predicting a set of question-answer pairs, where every plausible answer is paired with a disambiguated rewrite of the original question. To study this task, we construct AmbigNQ, a dataset covering 14,042 questions from NQ-open, an… Expand
20 Citations

Figures and Tables from this paper

Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction
  • 2
  • Highly Influenced
  • PDF
What Question Answering can Learn from Trivia Nerds
  • 4
  • PDF
PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them
  • 5
  • Highly Influenced
  • PDF
Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering
  • 44
  • PDF
QED: A Framework and Dataset for Explanations in Question Answering
  • 6
  • PDF
Resolving Intent Ambiguities by Retrieving Discriminative Clarifying Questions
  • 3
  • PDF
Reader-Guided Passage Reranking for Open-Domain Question Answering
  • 1
  • Highly Influenced
  • PDF
Joint Passage Ranking for Diverse Multi-Answer Retrieval
  • PDF
Generation-Augmented Retrieval for Open-domain Question Answering
  • 10
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 41 REFERENCES
Latent Retrieval for Weakly Supervised Open Domain Question Answering
  • 175
  • PDF
Asking Clarification Questions in Knowledge-Based Question Answering
  • J. Xu, Yuechen Wang, +5 authors X. Sun
  • Computer Science
  • EMNLP/IJCNLP
  • 2019
  • 7
  • PDF
Natural Questions: A Benchmark for Question Answering Research
  • 377
  • PDF
Reading Wikipedia to Answer Open-Domain Questions
  • 845
  • PDF
Can You Unpack That? Learning to Rewrite Questions-in-Context
  • 28
  • PDF
Asking Clarifying Questions in Open-Domain Information-Seeking Conversations
  • 86
  • PDF
A Discrete Hard EM Approach for Weakly Supervised Question Answering
  • 60
  • PDF
Semantic Parsing on Freebase from Question-Answer Pairs
  • 1,072
  • PDF
Crowdsourcing Question-Answer Meaning Representations
  • 39
  • PDF
...
1
2
3
4
5
...