Papers › Entity, Relation, and Event Extraction with Contextualized Span Representations

Entity, Relation, and Event Extraction with Contextualized Span Representations

8 Sep 2019IJCNLP 2019 11arXiv:1909.03546archive 2025-07-28

David Wadden, Ulme Wennberg, Yi Luan, Hannaneh Hajishirzi

We examine the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction. Our framework (called DyGIE++) accomplishes all tasks by enumerating, refining, and scoring text spans designed to capture local (within-sentence) and global (cross-sentence) context. Our framework achieves state-of-the-art results across all tasks, on four datasets from a variety of domains. We perform experiments comparing different techniques to construct span representations. Contextualized embeddings like BERT perform well at capturing relationships among entities in the same or adjacent sentences, while dynamic span graph updates model long-range cross-sentence relationships. For instance, propagating span representations via predicted coreference links can enable the model to disambiguate challenging entity mentions. Our code is publicly available at https://github.com/dwadden/dygiepp and can be easily adapted for new tasks or datasets.

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="1909.03546")

Code

Syntology Ran 0 of 7 code samples harvested from 1 repository linked to this paper; 7 have no recorded run.

By repository: community (archive-listed): 7 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.

dwadden/dygiepp officialmentioned in paperpytorchMIT report
diffbot/knowledge-net mentioned on GitHubtfMIT report
meiru-cam/coffee mentioned on GitHubpytorch report
rickltt/event_detection mentioned 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; 0 ran; 0 honoured the contract we drafted; 7 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.

7unverified

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 diffbot/knowledge-net. “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.

bert_embedding diffbot/knowledge-net/baselines/EMNLP2019/features.py community (archive-listed) unverified MIT (permissive) · 2a1b8b5cbb603a5f · report
bert_layers diffbot/knowledge-net/baselines/EMNLP2019/features.py community (archive-listed) unverified MIT (permissive) · b9b6c55cbf3e0233 · report
buildAnnotatedPassage diffbot/knowledge-net/dataset/evaluator.py community (archive-listed) unverified MIT (permissive) · b47d5106b6bd0ffd · report
checkField diffbot/knowledge-net/dataset/evaluator.py community (archive-listed) unverified MIT (permissive) · df9e14535042dcdf · report
coref_score diffbot/knowledge-net/baselines/EMNLP2019/global_features.py community (archive-listed) unverified MIT (permissive) · 8596fe57c887b433 · report
embedding diffbot/knowledge-net/baselines/EMNLP2019/features.py community (archive-listed) unverified MIT (permissive) · 340b033ce6245cbf · report
readKnowledgenetFile diffbot/knowledge-net/dataset/evaluator.py community (archive-listed) unverified MIT (permissive) · c77cf114994f5b70 · report

Tasks

Event ExtractionJoint Entity and Relation ExtractionNamed Entity RecognitionNamed Entity Recognition (NER)Relation ExtractionSentencenamed-entity-recognition

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 DyGIE++ Cross Sentence Yes #6 of 11 Archive leaderboard report
Joint Entity and Relation Extraction SciERC DyGIE++ Entity F1 67.50 #6 of 11 Archive leaderboard report
Joint Entity and Relation Extraction SciERC DyGIE++ Relation F1 48.40 #6 of 11 Archive leaderboard report
Relation Extraction ACE 2005 DYGIE++ Cross Sentence Yes #9 of 30 Archive leaderboard report
Relation Extraction ACE 2005 DYGIE++ NER Micro F1 88.6 #9 of 30 Archive leaderboard report
Relation Extraction ACE 2005 DYGIE++ RE Micro F1 63.4 #9 of 30 Archive leaderboard report
Relation Extraction ACE 2005 DYGIE++ Sentence Encoder BERT base #9 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

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

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