paper-with-me

Papers

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

2020-11-26 · ACL 2021 5 · Yifan Gao, Henghui Zhu, Patrick Ng, Cicero Nogueira dos santos, Zhiguo Wang, Feng Nan, Dejiao Zhang, Ramesh Nallapati, Andrew O. Arnold, Bing Xiang

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 possible interpretations of the question, and predict one or multiple plausible answers. When multiple plausible answers are found, the system should rewrite the question for each answer to resolve the ambiguity. In this paper, we present a model that aggregates and combines evidence from multiple passages to adaptively predict a single answer or a set of question-answer pairs for ambiguous questions. In addition, we propose a novel round-trip prediction approach to iteratively 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. Our model, named Refuel, achieves a new state-of-the-art performance on the AmbigQA dataset, and shows competitive performance on NQ-Open and TriviaQA. The proposed round-trip prediction is a model-agnostic general approach for answering ambiguous open-domain questions, which improves our Refuel as well as several baseline models. We release source code for our models and experiments at https://github.com/amzn/refuel-open-domain-qa.

📄 PDF Abstract BibTeX arXiv:2011.13137

Code (1)

amzn/refuel-open-domain-qa 공식 구현 pytorch

Tasks

Open-Domain Question AnsweringQuestion AnsweringTriviaQA

Similar Papers 제목 키워드 기반

Pseudo Ambiguous and Clarifying Questions Based on Sentence Structures Toward Clarifying Question Answering System

2022-05-01 · dialdoc (ACL) 2022 5 · Yuya Nakano, Seiya Kawano, Koichiro Yoshino, Katsuhito Sudoh 외

Question answering (QA) with disambiguation questions is essential for practical QA systems because user questions often do not contain information enough to find their answers. We call this task clarifying question answ…

Question AnsweringQuestion GenerationQuestion-GenerationSentence

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

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Open-domain questions are likely to be open-ended and ambiguous, leading to multiple valid answers. Existing approaches typically adopt the rerank-then-read framework, where a reader reads top-ranking evidence to predict…

valid

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

2021-10-16 · ACL 2022 5 · Zhihong Shao, Minlie Huang

Open-domain questions are likely to be open-ended and ambiguous, leading to multiple valid answers. Existing approaches typically adopt the rerank-then-read framework, where a reader reads top-ranking evidence to predict…

valid

Answering Ambiguous Questions with a Database of Questions, Answers, and Revisions

2023-08-16 · Haitian Sun, William W. Cohen, Ruslan Salakhutdinov

Many open-domain questions are under-specified and thus have multiple possible answers, each of which is correct under a different interpretation of the question. Answering such ambiguous questions is challenging, as it …

Passage RetrievalQuestion AnsweringRetrieval

Model Analysis & Evaluation for Ambiguous Question Answering

2023-05-21 · Konstantinos Papakostas, Irene Papadopoulou

Ambiguous questions are a challenge for Question Answering models, as they require answers that cover multiple interpretations of the original query. To this end, these models are required to generate long-form answers t…

modelQuestion Answering