Papers › A Partition Filter Network for Joint Entity and Relation Extraction

A Partition Filter Network for Joint Entity and Relation Extraction

27 Aug 2021EMNLP 2021 11arXiv:2108.12202archive 2025-07-28

Zhiheng Yan, Chong Zhang, Jinlan Fu, Qi Zhang, Zhongyu Wei

In joint entity and relation extraction, existing work either sequentially encode task-specific features, leading to an imbalance in inter-task feature interaction where features extracted later have no direct contact with those that come first. Or they encode entity features and relation features in a parallel manner, meaning that feature representation learning for each task is largely independent of each other except for input sharing. We propose a partition filter network to model two-way interaction between tasks properly, where feature encoding is decomposed into two steps: partition and filter. In our encoder, we leverage two gates: entity and relation gate, to segment neurons into two task partitions and one shared partition. The shared partition represents inter-task information valuable to both tasks and is evenly shared across two tasks to ensure proper two-way interaction. The task partitions represent intra-task information and are formed through concerted efforts of both gates, making sure that encoding of task-specific features is dependent upon each other. Experiment results on six public datasets show that our model performs significantly better than previous approaches. In addition, contrary to what previous work has claimed, our auxiliary experiments suggest that relation prediction is contributory to named entity prediction in a non-negligible way. The source code can be found at https://github.com/Coopercoppers/PFN.

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="2108.12202")

Code

Syntology Ran 5 of 7 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 4 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Coopercoppers/PFN officialmentioned in papermentioned 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

7 samples harvested; 5 ran; 0 honoured the contract we drafted; 2 have 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 · our draft was wrong
4ran
2unverified

Licence: 0 of the 7 samples are 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 Coopercoppers/PFN. “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.

LinearDropConnect Coopercoppers/PFN/model/pfn.py official repository ran MIT (permissive) · afec84e0faec9423 · report
cumsoftmax Coopercoppers/PFN/model/pfn.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 376d06bf379aaed4 · report
encoder Coopercoppers/PFN/model/pfn.py official repository ran MIT (permissive) · 3ea1177946b16e3f · report
ner_unit Coopercoppers/PFN/model/pfn.py official repository ran MIT (permissive) · a9b19a6a9feee024 · report
re_unit Coopercoppers/PFN/model/pfn.py official repository ran MIT (permissive) · 80cd984b7e023533 · report
PFN Coopercoppers/PFN/model/pfn.py official repository unverified MIT (permissive) · 8e459b63dc2fe2eb · report
pfn_unit Coopercoppers/PFN/model/pfn.py official repository unverified MIT (permissive) · e41a06253d12c0d0 · report

Tasks

Joint Entity and Relation ExtractionRelation ExtractionRelation PredictionRepresentation Learning

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 SciERC PFN Cross Sentence No #11 of 11 Archive leaderboard report
Joint Entity and Relation Extraction SciERC PFN Entity F1 66.8 #11 of 11 Archive leaderboard report
Joint Entity and Relation Extraction SciERC PFN RE+ Micro F1 38.4 #11 of 11 Archive leaderboard report
Relation Extraction ACE 2004 PFN Cross Sentence No #2 of 11 Archive leaderboard report
Relation Extraction ACE 2004 PFN NER Micro F1 89.3 #2 of 11 Archive leaderboard report
Relation Extraction ACE 2004 PFN RE+ Micro F1 62.5 #2 of 11 Archive leaderboard report
Relation Extraction ACE 2005 PFN Cross Sentence No #15 of 30 Archive leaderboard report
Relation Extraction ACE 2005 PFN NER Micro F1 89.0 #15 of 30 Archive leaderboard report
Relation Extraction ACE 2005 PFN RE+ Micro F1 66.8 #15 of 30 Archive leaderboard report
Relation Extraction ACE 2005 PFN Sentence Encoder ALBERT #15 of 30 Archive leaderboard report
Relation Extraction ADE Corpus PFN NER Macro F1 91.3 #1 of 1 Archive leaderboard report
Relation Extraction ADE Corpus PFN RE+ Macro F1 83.2 #1 of 1 Archive leaderboard report
Relation Extraction Adverse Drug Events (ADE) Corpus PFN (ALBERT XXL, no aggregation) NER Macro F1 91.3 #4 of 15 Archive leaderboard report
Relation Extraction Adverse Drug Events (ADE) Corpus PFN (ALBERT XXL, no aggregation) RE+ Macro F1 83.2 #4 of 15 Archive leaderboard report
Relation Extraction SciERC PFN NER Micro F1 66.8 #3 of 3 Archive leaderboard report
Relation Extraction SciERC PFN RE+ Micro F1 38.4 #3 of 3 Archive leaderboard report
Relation Extraction WebNLG PFN F1 93.6 #2 of 14 Archive leaderboard report
Relation Extraction WebNLG PFN NER Micro F1 98.0 #2 of 14 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

Partition Filter Network

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