Papers › Document-level Entity-based Extraction as Template Generation

Document-level Entity-based Extraction as Template Generation

10 Sep 2021EMNLP 2021 11arXiv:2109.04901archive 2025-07-28

Kung-Hsiang Huang, Sam Tang, Nanyun Peng

Document-level entity-based extraction (EE), aiming at extracting entity-centric information such as entity roles and entity relations, is key to automatic knowledge acquisition from text corpora for various domains. Most document-level EE systems build extractive models, which struggle to model long-term dependencies among entities at the document level. To address this issue, we propose a generative framework for two document-level EE tasks: role-filler entity extraction (REE) and relation extraction (RE). We first formulate them as a template generation problem, allowing models to efficiently capture cross-entity dependencies, exploit label semantics, and avoid the exponential computation complexity of identifying N-ary relations. A novel cross-attention guided copy mechanism, TopK Copy, is incorporated into a pre-trained sequence-to-sequence model to enhance the capabilities of identifying key information in the input document. Experiments done on the MUC-4 and SciREX dataset show new state-of-the-art results on REE (+3.26%), binary RE (+4.8%), and 4-ary RE (+2.7%) in F1 score.

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="2109.04901")

Code

Syntology Ran 0 of 10 code samples harvested from 1 repository linked to this paper; 10 have no recorded run.

By repository: official repository: 10 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

PlusLabNLP/TempGen officialmentioned in papermentioned on GitHubpytorchMIT 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

10 samples harvested; 0 ran; 0 honoured the contract we drafted; 10 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.

10unverified

Licence: 0 of the 10 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 PlusLabNLP/TempGen. “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.

bre_eval PlusLabNLP/TempGen/bre_eval.py official repository unverified MIT (permissive) · 179c577cfe250d9c · report
compute_mapping PlusLabNLP/TempGen/bre_eval.py official repository unverified MIT (permissive) · 1a6bd830af39580b · report
f1 PlusLabNLP/TempGen/ree_eval.py official repository unverified MIT (permissive) · 5dc251a1bb16c94f · report
format_inputs_outputs PlusLabNLP/TempGen/util.py official repository unverified MIT (permissive) · 86ce8222fefed159 · report
has_all_mentions PlusLabNLP/TempGen/bre_eval.py official repository unverified MIT (permissive) · cc66af9f533680f2 · report
phi_prop PlusLabNLP/TempGen/ree_eval.py official repository unverified MIT (permissive) · f7b10b434d2ca733 · report
phi_strict PlusLabNLP/TempGen/ree_eval.py official repository unverified MIT (permissive) · 6cc07897ce7e5e2b · report
process_entities PlusLabNLP/TempGen/convert_grit.py official repository unverified MIT (permissive) · 999a0e4f59e1e104 · report
scirex_eval PlusLabNLP/TempGen/scirex_eval.py official repository unverified MIT (permissive) · bc8299f646161453 · report
token2sub_tokens PlusLabNLP/TempGen/util.py official repository unverified MIT (permissive) · 6b87c15aae792362 · report

Tasks

4-ary Relation ExtractionBinary Relation ExtractionRole-filler Entity Extraction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
4-ary Relation Extraction SciREX TempGen Avg. F1 3.55 #1 of 1 Archive leaderboard report
Binary Relation Extraction SciREX TempGen Avg. F1 14.47 #1 of 1 Archive leaderboard report
Role-filler Entity Extraction MUC-4 TempGen Avg. F1 57.76 #1 of 1 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: TopK Copy

TopK Copy

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