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 ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 7 code samples harvested from 1 repository linked to this paper: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 5 ran (4 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Coopercoppers/PFN officialmentioned in papermentioned on GitHubpytorchSyntology: 7 samples, 5 ran (1 instrument-failed) · 2 unverified 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 (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is 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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

Coopercoppers/PFN official repository 7 samples, 5 ran (1 instrument-failed) · 2 unverified
LinearDropConnect model/pfn.py ran MIT (permissive) · afec84e0faec9423 · report fixture: returned LinearDropConnect · level recorded 2026-09-22
cumsoftmax model/pfn.py ran · our draft was wrong fingerprinted MIT (permissive) · 376d06bf379aaed4 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
encoder in 30 papers model/pfn.py ran MIT (permissive) · 3ea1177946b16e3f · report fixture: returned encoder · level recorded 2026-09-22
ner_unit model/pfn.py ran MIT (permissive) · a9b19a6a9feee024 · report fixture: signature h_ner:Tensor/3/float, h_share:Tensor/3/float, mask:Tensor/2/float · returned Tensor · level recorded 2026-09-24
re_unit model/pfn.py ran MIT (permissive) · 80cd984b7e023533 · report fixture: returned re_unit · level recorded 2026-09-22
PFN model/pfn.py unverified MIT (permissive) · 8e459b63dc2fe2eb · report
pfn_unit model/pfn.py unverified MIT (permissive) · e41a06253d12c0d0 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Partition Filter Network (graph method: Partition Filter Network). 7 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. PFN entry · level 0 · unverified · 8e459b63dc2fe2eb
  2. encoder model · level 1 · ran · 3ea1177946b16e3f
  3. ner_unit model · level 1 · ran · a9b19a6a9feee024
  4. re_unit model · level 1 · ran · 80cd984b7e023533
  5. pfn_unit model · level 0 · unverified · e41a06253d12c0d0
  6. LinearDropConnect helper · level 1 · ran · afec84e0faec9423
  7. cumsoftmax helper · level 1 · ran · our draft was wrong · 376d06bf379aaed4

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2108.12202") returns these assemblies with each brick's role and wiring (how to connect).

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