Papers › Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning

Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning

8 May 2021ACL 2021 5arXiv:2105.03654archive 2025-07-28

Xinyu Wang, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

Recent advances in Named Entity Recognition (NER) show that document-level contexts can significantly improve model performance. In many application scenarios, however, such contexts are not available. In this paper, we propose to find external contexts of a sentence by retrieving and selecting a set of semantically relevant texts through a search engine, with the original sentence as the query. We find empirically that the contextual representations computed on the retrieval-based input view, constructed through the concatenation of a sentence and its external contexts, can achieve significantly improved performance compared to the original input view based only on the sentence. Furthermore, we can improve the model performance of both input views by Cooperative Learning, a training method that encourages the two input views to produce similar contextual representations or output label distributions. Experiments show that our approach can achieve new state-of-the-art performance on 8 NER data sets across 5 domains.

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="2105.03654")

Code

Syntology Ran 0 of 4 code samples harvested from 1 repository linked to this paper; 4 have no recorded run.

By repository: official repository: 4 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.

modelscope/adaseq officialmentioned in paperpytorchApache-2.0 report
modelscope/AdaSeq officialpytorchApache-2.0 report
Alibaba-NLP/CLNER mentioned in papermentioned on GitHubpytorchNOASSERTION 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

4 samples harvested; 0 ran; 0 honoured the contract we drafted; 4 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.

4unverified

Licence: 0 of the 4 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 modelscope/AdaSeq. “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.

bio2span modelscope/AdaSeq/adaseq/models/utils.py official repository unverified Apache-2.0 (permissive) · e17e0c84478d9fdf · report
convert2span modelscope/AdaSeq/adaseq/models/utils.py official repository unverified Apache-2.0 (permissive) · 1c09f1b2a1673ff7 · report
fix_tag_sequence_error modelscope/AdaSeq/adaseq/models/utils.py official repository unverified Apache-2.0 (permissive) · d1402dd2781d2ac7 · report
get_member_set modelscope/AdaSeq/adaseq/metainfo.py official repository unverified Apache-2.0 (permissive) · 1bab6e044bc7a5f1 · report

Tasks

Chinese Named Entity RecognitionChunkingNamed Entity RecognitionNamed Entity Recognition (NER)RetrievalSentence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Chinese Named Entity Recognition MSRA BERT-CRF (Replicated in AdaSeq) F1 96.69 #2 of 21 Archive leaderboard report
Chinese Named Entity Recognition Resume NER BERT-CRF (Replicated in AdaSeq) F1 96.87 #1 of 13 Archive leaderboard report
Chinese Named Entity Recognition Weibo NER BERT-CRF (Replicated in AdaSeq) F1 72.77 #1 of 18 Archive leaderboard report
Chunking CoNLL 2000 BERT-CRF (Replicated in AdaSeq) Exact Span F1 97.18 #2 of 9 Archive leaderboard report
Named Entity Recognition (NER) BC5CDR CL-L2 F1 90.99 #3 of 16 Archive leaderboard report
Named Entity Recognition (NER) CMeEE BERT-CRF (Replicated in AdaSeq) F1 68.97 #1 of 2 Archive leaderboard report
Named Entity Recognition (NER) CoNLL 2003 (English) CL-KL F1 93.85 #8 of 73 Archive leaderboard report
Named Entity Recognition (NER) CoNLL 2003 (English) BERT-CRF (Replicated in AdaSeq) F1 93.35 #25 of 73 Archive leaderboard report
Named Entity Recognition (NER) CoNLL++ CL-KL F1 94.81 #5 of 11 Archive leaderboard report
Named Entity Recognition (NER) NCBI-disease CL-KL F1 88.96 #7 of 26 Archive leaderboard report
Named Entity Recognition (NER) WNUT 2016 CL-KL F1 58.98 #2 of 7 Archive leaderboard report
Named Entity Recognition (NER) WNUT 2017 CL-KL F1 60.45 #1 of 23 Archive leaderboard report
Named Entity Recognition (NER) WNUT 2017 BERT-CRF (Replicated in AdaSeq) F1 59.69 #3 of 23 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