Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction

by   Yifan Gao, et al.

In open-domain question answering, questions are highly likely to be ambiguous because users may not know the scope of relevant topics when formulating them. Therefore, a system needs to find every possible interpretation of the question, and propose a set of disambiguated question-answer pairs. In this paper, we present a model that aggregates and combines evidence from multiple passages to generate question-answer pairs. Particularly, our model reads a large number of passages to find as many interpretations as possible. In addition, we propose a novel round-trip prediction approach to generate additional interpretations that our model fails to find in the first pass, and then verify and filter out the incorrect question-answer pairs to arrive at the final disambiguated output. On the recently introduced AmbigQA open-domain question answering dataset, our model, named Refuel, achieves a new state-of-the-art, outperforming the previous best model by a large margin. We also conduct comprehensive analyses to validate the effectiveness of our proposed round-trip prediction.



There are no comments yet.


page 1

page 2

page 3

page 4


AmbigQA: Answering Ambiguous Open-domain Questions

Ambiguity is inherent to open-domain question answering; especially when...

Learning to Answer Ambiguous Questions with Knowledge Graph

In the task of factoid question answering over knowledge base, many ques...

Dynamic Coattention Networks For Question Answering

Several deep learning models have been proposed for question answering. ...

Training IBM Watson using Automatically Generated Question-Answer Pairs

IBM Watson is a cognitive computing system capable of question answering...

Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering

End-to-end neural models have made significant progress in question answ...

Tackling Multi-Answer Open-Domain Questions via a Recall-then-Verify Framework

Open domain questions are likely to be open-ended and ambiguous, leading...

Don't Read Too Much into It: Adaptive Computation for Open-Domain Question Answering

Most approaches to Open-Domain Question Answering consist of a light-wei...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.