--- title: "Neural Cross-Lingual Named Entity Recognition — Xie 2018" description: "The paper tackles named entity recognition for languages with no labeled data, transferring knowledge from English annotations." authors: ["Jiateng Xie", "Zhilin Yang", "Graham Neubig", "Noah A. Smith", "Jaime Carbonell"] year: 2018 venue: "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing" source: "https://aclanthology.org/D18-1034/" doi: "10.18653/v1/d18-1034" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/xie-2018-neural-cross-lingual-named-entity/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/xie-2018-neural-cross-lingual-named-entity/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2018](https://md.research.elamur.ai/free/en/papers/2018/page/3/) / Neural Cross-Lingual Named Entity Recognition with Minimal Resources # Neural Cross-Lingual Named Entity Recognition with Minimal Resources **Authors:** Jiateng Xie, [Zhilin Yang](https://md.research.elamur.ai/free/en/authors/zhilin-yang/), [Graham Neubig](https://md.research.elamur.ai/free/en/authors/graham-neubig/), [Noah A. Smith](https://md.research.elamur.ai/free/en/authors/noah-a-smith/), [Jaime Carbonell](https://md.research.elamur.ai/free/en/authors/jaime-carbonell/) · **Year:** 2018 · **Venue:** Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/D18-1034/) · [PDF](https://aclanthology.org/D18-1034.pdf) · [DOI 10.18653/v1/d18-1034](https://doi.org/10.18653/v1/d18-1034) · [OpenAlex](https://openalex.org/W2889191148) **Citations:** 156 citations (openalex-snapshot · 2026-10-14) · [91](#cited-by) in our library, of the 140884 papers whose bibliographies we read ## Summary The paper tackles named entity recognition for languages with no labeled data, transferring knowledge from English annotations. It addresses two obstacles: mapping vocabulary between languages cheaply, and handling differences in word order. For vocabulary, the authors align separately trained monolingual embeddings into a shared space using a small seed dictionary (orthogonal Procrustes plus iterative self-learning). Each English training word is then replaced by its nearest target-language neighbour under the CSLS metric, and the entity tags are carried over. Because the synthetic training data contains real target-language words, the tagger can still use character-level features. For word order, they add a self-attention layer to a Bi-LSTM-CRF tagger so it can gather context more flexibly. On CoNLL 2002/2003 data, the approach gives state-of-the-art cross-lingual results for Spanish and Dutch and competitive results for German, without Wikipedia or parallel corpora. Uyghur experiments show it still helps in a truly low-resource setting, although poor embeddings limit performance. The work lowers the resource requirements for building NER in under-served languages. ## Key points - Requirements are minimal: source-language labels, monolingual corpora in both languages, and a small dictionary, which can be pre-existing or induced without supervision. Embedding alignment uses k = 3 self-learning refinement steps. - In an internal comparison of embedding-use strategies, translating the training data outperformed both the shared-space and word-replacement variants. F1 scores were 69.21 for Spanish, 69.39 for Dutch, and 53.94 for German, where the shared-space variant reached only 43.73. - On Uyghur (199 DARPA LORELEI "unsequestered set" documents), the method used just a 5K dictionary and fastText/GloVe embeddings. It scored 26.38 F1 with self-attention, compared with 27.20 for Mayhew et al. (2017) using English data, Wikipedia and a 100K dictionary. - The best Uyghur result, 32.09 F1, came from combining Mayhew et al.'s dictionary with embedding-based translation of uncovered words. - Fully unsupervised alignment (adversarial training or identical strings) failed for Uyghur, with F1 around 10. The authors attribute this to low-quality embeddings, the distance between the languages, and the Arabic script. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/) Topics: [Named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/) ## Cited by Cited by 91 papers of our library cite it (of the 140884 whose bibliographies we read); 6 of them have a page here, 85 not yet. - [Choosing Transfer Languages for Cross-Lingual Learning](https://md.research.elamur.ai/free/en/papers/lin-2019-choosing-transfer-languages-cross-lingual/) - [Massively Multilingual Transfer for NER](https://md.research.elamur.ai/free/en/papers/rahimi-2019-massively-multilingual-transfer-ner/) - [Cross-lingual Transfer Learning for Multilingual Task Oriented Dialog](https://md.research.elamur.ai/free/en/papers/schuster-2019-cross-lingual-transfer-learning-multilingual/) - [Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT](https://md.research.elamur.ai/free/en/papers/wu-2019-beto-bentz-becas-surprising-cross/) - [End-to-End Slot Alignment and Recognition for Cross-Lingual NLU](https://md.research.elamur.ai/free/en/papers/xu-2020-end-end-slot-alignment-recognition/) - [Handling Syntactic Divergence in Low-resource Machine Translation](https://md.research.elamur.ai/free/en/papers/zhou-2019-handling-syntactic-divergence-low-resource/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{xie2018neural, title = {{Neural Cross-Lingual Named Entity Recognition with Minimal Resources}}, author = {Xie, Jiateng and Yang, Zhilin and Neubig, Graham and Smith, Noah A. and Carbonell, Jaime}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, year = {2018}, doi = {10.18653/v1/d18-1034}, url = {https://doi.org/10.18653/v1/d18-1034} } ``` - [← previous Neural Cross-Lingual Coreference Resolution And Its Application To Entity Linking](https://md.research.elamur.ai/free/en/papers/kundu-2018-neural-cross-lingual-coreference-resolution/) - [next → Neural Document Summarization by Jointly Learning to Score and Select Sentences](https://md.research.elamur.ai/free/en/papers/zhou-2018-neural-document-summarization-jointly-learning/) - [↑ back to papers of 2018](https://md.research.elamur.ai/free/en/papers/2018/page/3/) ## References 6 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. \#\# Acknowledgments We thank Stephen Mayhew for sharing the data, and Zihang Dai for meaningful discussion. This research was sponsored by Defense Advanced Research Projects Agency Information Innovation Office (I2O) under the Low Resource Languages for Emergent Incidents (LORELEI) program, issued by… [find](https://scholar.google.com/scholar?q=%5C%23%5C%23+Acknowledgments+We+thank+Stephen+Mayhew+for+sharing+the+data%2C+and+Zihang+Dai+for+meaningful+discussion%2E+This+research+was+sponsored+by+Defense+Advanced+Research+Projects+Agency+Information+Innova) 2. Waleed Ammar, George Mulcaire, Miguel Ballesteros, Chris Dyer, and Noah A. Smith. 2016a. Many languages, one parser. Transactions of the Association for Computational Linguistics, 4:431–444. [find](https://scholar.google.com/scholar?q=Waleed+Ammar%2C+George+Mulcaire%2C+Miguel+Ballesteros%2C+Chris+Dyer%2C+and+Noah+A%2E+Smith%2E+2016a%2E+Many+languages%2C+one+parser%2E+Transactions+of+the+Association+for+Computational+Linguistics%2C+4%3A431%E2%80%93444%2E) [our card](https://md.research.elamur.ai/free/en/papers/ammar-2016-many-languages-one-parser/) 3. Waleed Ammar, George Mulcaire, Yulia Tsvetkov, Guillaume Lample, Chris Dyer, and Noah A. Smith. 2016b. Massively multilingual word embeddings. [https://arxiv.org/pdf/1602.01925](https://arxiv.org/pdf/1602.01925). [↗](https://arxiv.org/pdf/1602.01925) [our card](https://md.research.elamur.ai/free/en/papers/ammar-2016-massively-multilingual-word-embeddings/) 4. Mikel Artetxe, Gorka Labaka, and Eneko Agirre. 2016. Learning principled bilingual mappings of word embeddings while preserving monolingual invariance. In EMNLP, pages 2289–2294. [find](https://scholar.google.com/scholar?q=Mikel+Artetxe%2C+Gorka+Labaka%2C+and+Eneko+Agirre%2E+2016%2E+Learning+principled+bilingual+mappings+of+word+embeddings+while+preserving+monolingual+invariance%2E+In+EMNLP%2C+pages+2289%E2%80%932294%2E) [our card](https://md.research.elamur.ai/free/en/papers/artetxe-2016-learning-principled-bilingual-mappings-word/) 5. Mikel Artetxe, Gorka Labaka, and Eneko Agirre. 2017. Learning bilingual word embeddings with (almost) no bilingual data. In ACL, pages 451–462. [find](https://scholar.google.com/scholar?q=Mikel+Artetxe%2C+Gorka+Labaka%2C+and+Eneko+Agirre%2E+2017%2E+Learning+bilingual+word+embeddings+with+%28almost%29+no+bilingual+data%2E+In+ACL%2C+pages+451%E2%80%93462%2E) [our card](https://md.research.elamur.ai/free/en/papers/artetxe-2017-learning-bilingual-word-embeddings-almost/) 6. Akash Bharadwaj, David Mortensen, Chris Dyer, and Jaime Carbonell. 2016. Phonologically aware neural model for named entity recognition in low resource transfer settings. In EMNLP, pages 1462– 1472. \#\# Conclusion [find](https://scholar.google.com/scholar?q=Akash+Bharadwaj%2C+David+Mortensen%2C+Chris+Dyer%2C+and+Jaime+Carbonell%2E+2016%2E+Phonologically+aware+neural+model+for+named+entity+recognition+in+low+resource+transfer+settings%2E+In+EMNLP%2C+pages+1462%E2%80%93+1472%2E+%5C)