Papers › Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering

Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering

22 Aug 2019IJCNLP 2019 11arXiv:1908.08167archive 2025-07-28

Zhiguo Wang, Patrick Ng, Xiaofei Ma, Ramesh Nallapati, Bing Xiang

BERT model has been successfully applied to open-domain QA tasks. However, previous work trains BERT by viewing passages corresponding to the same question as independent training instances, which may cause incomparable scores for answers from different passages. To tackle this issue, we propose a multi-passage BERT model to globally normalize answer scores across all passages of the same question, and this change enables our QA model find better answers by utilizing more passages. In addition, we find that splitting articles into passages with the length of 100 words by sliding window improves performance by 4%. By leveraging a passage ranker to select high-quality passages, multi-passage BERT gains additional 2%. Experiments on four standard benchmarks showed that our multi-passage BERT outperforms all state-of-the-art models on all benchmarks. In particular, on the OpenSQuAD dataset, our model gains 21.4% EM and 21.5% F₁ over all non-BERT models, and 5.8% EM and 6.5% F₁ over BERT-based models.

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

AllArticlesOpen-Domain Question AnsweringQuestion Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open-Domain Question Answering SearchQA Multi-passage BERT EM 65.1 #3 of 14 Archive leaderboard report
Question Answering Quasart-T Multi-passage BERT EM 51.1 #4 of 7 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.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

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