Papers › Packed Levitated Marker for Entity and Relation Extraction

Packed Levitated Marker for Entity and Relation Extraction

13 Sep 2021ACL 2022 5arXiv:2109.06067archive 2025-07-28

Deming Ye, Yankai Lin, Peng Li, Maosong Sun

Recent entity and relation extraction works focus on investigating how to obtain a better span representation from the pre-trained encoder. However, a major limitation of existing works is that they ignore the interrelation between spans (pairs). In this work, we propose a novel span representation approach, named Packed Levitated Markers (PL-Marker), to consider the interrelation between the spans (pairs) by strategically packing the markers in the encoder. In particular, we propose a neighborhood-oriented packing strategy, which considers the neighbor spans integrally to better model the entity boundary information. Furthermore, for those more complicated span pair classification tasks, we design a subject-oriented packing strategy, which packs each subject and all its objects to model the interrelation between the same-subject span pairs. The experimental results show that, with the enhanced marker feature, our model advances baselines on six NER benchmarks, and obtains a 4.1%-4.3% strict relation F1 improvement with higher speed over previous state-of-the-art models on ACE04 and ACE05.

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="2109.06067")

Code

Syntology Ran 3 of 9 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · our draft was wrong.

By repository: official repository: 8 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.

thunlp/pl-marker officialmentioned in papermentioned on GitHubpytorchMIT report
tomaarsen/spanmarkerner mentioned on GitHubpytorchApache-2.0 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

9 samples harvested; 3 ran; 1 honoured the contract we drafted; 6 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 · honoured contract
2ran · our draft was wrong
6unverified

Licence: 1 of the 9 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 thunlp/pl-marker. 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.

swish thunlp/pl-marker/transformers/src/transformers/activations.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 0f786c407fb1ee4c · report
to_list thunlp/pl-marker/run_levitatedpair.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 9df40357afea56cc · report
gelu_new thunlp/pl-marker/transformers/src/transformers/activations.py official repository ran · honoured contract fingerprinted MIT (permissive) · 77601724cad03f95 · report
evaluate_conll thunlp/pl-marker/conll.py official repository unverified MIT (permissive) · 15f2da988c1b38ad · report
get_doc_key thunlp/pl-marker/conll.py official repository unverified MIT (permissive) · f300a33fe05fc609 · report
get_original_token thunlp/pl-marker/preprocess_ontonotes.py official repository unverified MIT (permissive) · e54f1fe179178f6b · report
normalize_word thunlp/pl-marker/preprocess_ontonotes.py official repository unverified MIT (permissive) · ba4eb9ed094dc59e · report
official_conll_eval thunlp/pl-marker/conll.py official repository unverified MIT (permissive) · b12f4137ab9599e7 · report
load_tf_weights_in_albert identical code first harvested elsewhere unverified licence of this copy not recorded · 0acb90d02eadd73f · report

Tasks

Joint Entity and Relation ExtractionNamed Entity Recognition (NER)Relation Extraction

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 PL-Marker Cross Sentence Yes #1 of 11 Archive leaderboard report
Joint Entity and Relation Extraction SciERC PL-Marker Entity F1 69.9 #1 of 11 Archive leaderboard report
Joint Entity and Relation Extraction SciERC PL-Marker RE+ Micro F1 41.6 #1 of 11 Archive leaderboard report
Joint Entity and Relation Extraction SciERC PL-Marker Relation F1 53.2 #1 of 11 Archive leaderboard report
Named Entity Recognition (NER) CoNLL 2003 (English) PL-Marker F1 94.0 #7 of 73 Archive leaderboard report
Named Entity Recognition (NER) Few-NERD (SUP) PL-Marker F1-Measure 70.9 #1 of 6 Archive leaderboard report
Named Entity Recognition (NER) Few-NERD (SUP) PL-Marker Precision 71.2 #1 of 6 Archive leaderboard report
Named Entity Recognition (NER) Few-NERD (SUP) PL-Marker Recall 70.6 #1 of 6 Archive leaderboard report
Named Entity Recognition (NER) Ontonotes v5 (English) PL-Marker F1 91.9 #2 of 28 Archive leaderboard report
Named Entity Recognition (NER) Ontonotes v5 (English) PL-Marker Precision 92.0 #2 of 28 Archive leaderboard report
Named Entity Recognition (NER) Ontonotes v5 (English) PL-Marker Recall 91.7 #2 of 28 Archive leaderboard report
Relation Extraction ACE 2004 PL-Marker Cross Sentence Yes #1 of 11 Archive leaderboard report
Relation Extraction ACE 2004 PL-Marker NER Micro F1 90.4 #1 of 11 Archive leaderboard report
Relation Extraction ACE 2004 PL-Marker RE Micro F1 69.7 #1 of 11 Archive leaderboard report
Relation Extraction ACE 2004 PL-Marker RE+ Micro F1 66.5 #1 of 11 Archive leaderboard report
Relation Extraction ACE 2005 PL-Marker Cross Sentence Yes #2 of 30 Archive leaderboard report
Relation Extraction ACE 2005 PL-Marker NER Micro F1 91.1 #2 of 30 Archive leaderboard report
Relation Extraction ACE 2005 PL-Marker RE Micro F1 73.0 #2 of 30 Archive leaderboard report
Relation Extraction ACE 2005 PL-Marker RE+ Micro F1 71.1 #2 of 30 Archive leaderboard report
Relation Extraction ACE 2005 PL-Marker Sentence Encoder ALBERT #2 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.

Methods

Introduced by this paper: Packed Levitated Markers

Absolute Position EncodingsPacked Levitated MarkersPosition-Wise Feed-Forward LayerTransformer

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