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 Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

microsoft/vert-papers officialpytorch 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

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