Papers › Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resources

Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resources

14 Nov 2019arXiv:1911.06161archive 2025-07-28

Qianhui Wu, Zijia Lin, Guoxin Wang, Hui Chen, Börje F. Karlsson, Biqing Huang, Chin-Yew Lin

For languages with no annotated resources, transferring knowledge from rich-resource languages is an effective solution for named entity recognition (NER). While all existing methods directly transfer from source-learned model to a target language, in this paper, we propose to fine-tune the learned model with a few similar examples given a test case, which could benefit the prediction by leveraging the structural and semantic information conveyed in such similar examples. To this end, we present a meta-learning algorithm to find a good model parameter initialization that could fast adapt to the given test case and propose to construct multiple pseudo-NER tasks for meta-training by computing sentence similarities. To further improve the model's generalization ability across different languages, we introduce a masking scheme and augment the loss function with an additional maximum term during meta-training. We conduct extensive experiments on cross-lingual named entity recognition with minimal resources over five target languages. The results show that our approach significantly outperforms existing state-of-the-art methods across the board.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

microsoft/vert-papers officialpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Decomposed Meta-Learning for Few-Shot Named Entity Recognition (arXiv:2204.05751; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Cross-Lingual NERCross-Lingual TransferMeta-LearningNERNamed Entity RecognitionNamed Entity Recognition (NER)Sentencenamed-entity-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Lingual NER CoNLL Dutch Meta-Cross F1 80.44 #6 of 10 Archive leaderboard report
Cross-Lingual NER CoNLL Dutch Base Model F1 79.57 #8 of 10 Archive leaderboard report
Cross-Lingual NER CoNLL German Meta-Cross F1 73.16 #6 of 10 Archive leaderboard report
Cross-Lingual NER CoNLL German Base Model F1 70.79 #8 of 10 Archive leaderboard report
Cross-Lingual NER CoNLL Spanish Meta-Cross F1 76.75 #6 of 10 Archive leaderboard report
Cross-Lingual NER CoNLL Spanish Base Model F1 74.59 #9 of 10 Archive leaderboard report
Cross-Lingual NER Europeana French Meta-Cross F1 55.3 #1 of 2 Archive leaderboard report
Cross-Lingual NER Europeana French Base Model F1 50.89 #2 of 2 Archive leaderboard report
Cross-Lingual NER MSRA Meta-Cross F1 77.89 #1 of 2 Archive leaderboard report
Cross-Lingual NER MSRA Base Model F1 76.42 #2 of 2 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

Test

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