Papers › UnitedQA: A Hybrid Approach for Open Domain Question Answering

UnitedQA: A Hybrid Approach for Open Domain Question Answering

1 Jan 2021ACL 2021 5arXiv:2101.00178archive 2025-07-28

Hao Cheng, Yelong Shen, Xiaodong Liu, Pengcheng He, Weizhu Chen, Jianfeng Gao

To date, most of recent work under the retrieval-reader framework for open-domain QA focuses on either extractive or generative reader exclusively. In this paper, we study a hybrid approach for leveraging the strengths of both models. We apply novel techniques to enhance both extractive and generative readers built upon recent pretrained neural language models, and find that proper training methods can provide large improvement over previous state-of-the-art models. We demonstrate that a simple hybrid approach by combining answers from both readers can efficiently take advantages of extractive and generative answer inference strategies and outperforms single models as well as homogeneous ensembles. Our approach outperforms previous state-of-the-art models by 3.3 and 2.7 points in exact match on NaturalQuestions and TriviaQA respectively.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Open-Domain Question AnsweringQuestion AnsweringRetrievalTriviaQA

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open-Domain Question Answering Natural Questions UnitedQA (Hybrid) Exact Match 54.7 #4 of 5 Archive leaderboard report
Open-Domain Question Answering TriviaQA UnitedQA (Hybrid) Exact Match 70.5 #1 of 1 Archive leaderboard report
Question Answering EfficientQA dev UnitedQA Accuracy 54.1 #1 of 1 Archive leaderboard report
Question Answering EfficientQA test UnitedQA Accuracy 54 #1 of 1 Archive leaderboard report
Question Answering Natural Questions (long) UnitedQA (Hybrid) EM 54.7 #12 of 13 Archive leaderboard report
Question Answering TriviaQA UnitedQA (Hybrid reader) F1 70.3 #54 of 56 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections