Papers › Simple Applications of BERT for Ad Hoc Document Retrieval

Simple Applications of BERT for Ad Hoc Document Retrieval

26 Mar 2019arXiv:1903.10972archive 2025-07-28

Wei Yang, Haotian Zhang, Jimmy Lin

Following recent successes in applying BERT to question answering, we explore simple applications to ad hoc document retrieval. This required confronting the challenge posed by documents that are typically longer than the length of input BERT was designed to handle. We address this issue by applying inference on sentences individually, and then aggregating sentence scores to produce document scores. Experiments on TREC microblog and newswire test collections show that our approach is simple yet effective, as we report the highest average precision on these datasets by neural approaches that we are aware of.

PaperPDFCode

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

Code

castorini/birch mentioned on GitHubpytorch report
kasys-lab/anserini-kasys mentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Ad-Hoc Information RetrievalQuestion AnsweringRetrievalSentence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Ad-Hoc Information Retrieval TREC Robust04 BERT FT(Microblog) MAP 0.3278 #17 of 21 Archive leaderboard report
Ad-Hoc Information Retrieval TREC Robust04 BERT FT(Microblog) P@20 0.4287 #17 of 21 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