Papers › A Frustratingly Easy Approach for Entity and Relation Extraction

A Frustratingly Easy Approach for Entity and Relation Extraction

24 Oct 2020NAACL 2021 4arXiv:2010.12812archive 2025-07-28

Zexuan Zhong, Danqi Chen

End-to-end relation extraction aims to identify named entities and extract relations between them. Most recent work models these two subtasks jointly, either by casting them in one structured prediction framework, or performing multi-task learning through shared representations. In this work, we present a simple pipelined approach for entity and relation extraction, and establish the new state-of-the-art on standard benchmarks (ACE04, ACE05 and SciERC), obtaining a 1.7%-2.8% absolute improvement in relation F1 over previous joint models with the same pre-trained encoders. Our approach essentially builds on two independent encoders and merely uses the entity model to construct the input for the relation model. Through a series of careful examinations, we validate the importance of learning distinct contextual representations for entities and relations, fusing entity information early in the relation model, and incorporating global context. Finally, we also present an efficient approximation to our approach which requires only one pass of both entity and relation encoders at inference time, achieving an 8-16× speedup with a slight reduction in accuracy.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2010.12812")

Code

Syntology Ran 3 of 4 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 3 samples from 1 repository, 3 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

princeton-nlp/PURE officialmentioned on GitHubpytorch 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

4 samples harvested; 3 ran; 1 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
1ran · fixture could not drive it
1unverified

Licence: 1 of the 4 samples is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from princeton-nlp/PURE. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

compute_f1 princeton-nlp/PURE/run_relation.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · f39c75c8e38877a5 · report
convert_examples_to_features princeton-nlp/PURE/run_relation.py official repository ran · our draft was wrong MIT (permissive) · b4727e3523efb30b · report
evaluate princeton-nlp/PURE/run_entity.py official repository ran · honoured contract MIT (permissive) · 136782e0f93a2faa · report
simple_accuracy identical code first harvested elsewhere unverified licence of this copy not recorded · 3c241ecfe3749a6d · report

Tasks

Joint Entity and Relation ExtractionMulti-Task LearningNamed Entity Recognition (NER)Relation ExtractionStructured Prediction

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Joint Entity and Relation Extraction ACE 2005 Ours: cross-sentence ALB Relation F1 62.2 #1 of 1 Archive leaderboard report
Joint Entity and Relation Extraction SciERC Ours: cross-sentence Cross Sentence Yes #5 of 11 Archive leaderboard report
Joint Entity and Relation Extraction SciERC Ours: cross-sentence Entity F1 68.9 #5 of 11 Archive leaderboard report
Joint Entity and Relation Extraction SciERC Ours: cross-sentence RE+ Micro F1 36.7 #5 of 11 Archive leaderboard report
Joint Entity and Relation Extraction SciERC Ours: cross-sentence Relation F1 50.1 #5 of 11 Archive leaderboard report
Named Entity Recognition (NER) ACE 2004 Ours: cross-sentence ALB F1 90.3 #1 of 9 Archive leaderboard report
Named Entity Recognition (NER) ACE 2004 Ours: cross-sentence ALB Multi-Task Supervision y #1 of 9 Archive leaderboard report
Named Entity Recognition (NER) ACE 2005 Ours: cross-sentence ALB F1 90.9 #1 of 20 Archive leaderboard report
Named Entity Recognition (NER) SciERC Ours: cross-sentence F1 68.2 #4 of 7 Archive leaderboard report
Relation Extraction ACE 2004 Ours: cross-sentence ALB Cross Sentence Yes #3 of 11 Archive leaderboard report
Relation Extraction ACE 2004 Ours: cross-sentence ALB NER Micro F1 90.3 #3 of 11 Archive leaderboard report
Relation Extraction ACE 2004 Ours: cross-sentence ALB RE Micro F1 66.1 #3 of 11 Archive leaderboard report
Relation Extraction ACE 2004 Ours: cross-sentence ALB RE+ Micro F1 62.2 #3 of 11 Archive leaderboard report
Relation Extraction ACE 2005 Ours: cross-sentence ALB Cross Sentence Yes #5 of 30 Archive leaderboard report
Relation Extraction ACE 2005 Ours: cross-sentence ALB NER Micro F1 90.9 #5 of 30 Archive leaderboard report
Relation Extraction ACE 2005 Ours: cross-sentence ALB RE Micro F1 69.4 #5 of 30 Archive leaderboard report
Relation Extraction ACE 2005 Ours: cross-sentence ALB Sentence Encoder ALBERT #5 of 30 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