UniTrans : Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data

Wu, Qianhui; Lin, Zijia; Karlsson, Börje F.; Huang, Biqing; Lou, Jian–Guang

doi:10.24963/ijcai.2020/543

Cited by 28 publications

(30 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All datasets are labeled with 4 entity types: PER, ORG, LOC, MISC. Each of them is split into training, validation and test sets following (Wu et al, 2020b). We use three MRC datasets in target languages: MLQA (es) (Lewis et al, 2019), XQuAD (de) (Artetxe et al, 2019), and SQuAD (en) (Rajpurkar et al, 2016).…”

Section: Data Preparationmentioning

confidence: 99%

See 2 more Smart Citations

Target-oriented Fine-tuning for Zero-Resource Named Entity Recognition

Zhang¹,

Meng²,

Chen³

et al. 2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

Zero-resource named entity recognition (NER) severely suffers from data scarcity in a specific domain or language. Most studies on zero-resource NER transfer knowledge from various data by fine-tuning on different auxiliary tasks. However, how to properly select training data and fine-tuning tasks is still an open problem. In this paper, we tackle the problem by transferring knowledge from three aspects, i.e., domain, language and task, and strengthening connections among them. Specifically, we propose four practical guidelines to guide knowledge transfer and task finetuning. Based on these guidelines, we design a target-oriented fine-tuning (TOF) framework to exploit various data from three aspects in a unified training manner. Experimental results on six benchmarks show that our method yields consistent improvements over baselines in both cross-domain and cross-lingual scenarios. Particularly, we achieve new state-of-theart performance on five benchmarks.

show abstract

Section: Data Preparationmentioning

confidence: 99%

“…UniTrans. Wu et al (2020b) unify data transfer and model transfer for cross-lingual NER. mCell LSTM.…”

Section: Systemsmentioning

confidence: 99%

See 1 more Smart Citation

Target-oriented Fine-tuning for Zero-Resource Named Entity Recognition

Zhang¹,

Meng²,

Chen³

et al. 2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

show abstract

“…Following Xie et al (2018) and Wu et al (2020), we apply techniques from Lample et al (2017) to translate our primary language training data wordby-word into our secondary languages, and directly copy the entity label of each primary language word to its corresponding translated word. Using embeddings from Bojanowski et al (2017), we learn a mapping, using the MUSE library, from the primary to the secondary language making use of identical character strings between the two languages.…”

Section: Experimental Approachmentioning

confidence: 99%

Shared Task 1 System Description : Exploring different approaches for multilingual tasks

Kalyan¹,

Tan²,

Tan³

et al. 2021

Proceedings of the 4th Workshop on Challenges and Applications of Automated Extraction of Socio-Political Events From Text (CAS

View full text Add to dashboard Cite

The aim of the CASE 2021 Shared Task 1 was to detect and classify socio-political and crisis event information at document, sentence, cross-sentence, and token levels in a multilingual setting, with each of these subtasks being evaluated separately in each test language. Our submission contained entries in all of the subtasks, and the scores obtained validated our research finding: That the multilingual aspect of the tasks should be embraced, so that modeling and training regimes use the multilingual nature of the tasks to their mutual benefit, rather than trying to tackle the different languages separately. Our code is available at https:

show abstract

“…Existing approaches to cross-lingual NER can be roughly grouped into two main categories: instance-based transfer via machine translation (MT) and label projection (Mayhew et al, 2017;Jain et al, 2019), and model-based transfer with aligned cross-lingual word representations or pretrained multilingual language models (Joty et al, 2017;Baumann, 2019;Conneau et al, 2020;. Recently, Wu et al (2020) unify instance-based and model-based transfer via knowledge distillation.…”

Section: Introductionmentioning

confidence: 99%

MulDA: A Multilingual Data Augmentation Framework for Low-Resource Cross-Lingual NER

Liu¹,

Ding²,

Joty³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Named Entity Recognition (NER) for lowresource languages is a both practical and challenging research problem. This paper addresses zero-shot transfer for cross-lingual NER, especially when the amount of sourcelanguage training data is also limited. The paper first proposes a simple but effective labeled sequence translation method to translate source-language training data to target languages and avoids problems such as word order change and entity span determination. With the source-language data as well as the translated data, a generation-based multilingual data augmentation method is introduced to further increase diversity by generating synthetic labeled data in multiple languages. These augmented data enable the language model based NER models to generalize better with both the language-specific features from the target-language synthetic data and the language-independent features from multilingual synthetic data. An extensive set of experiments were conducted to demonstrate encouraging cross-lingual transfer performance of the new research on a wide variety of target languages. 1 * Equal contribution, order decided by coin flip. Linlin Liu and Bosheng Ding are under the Joint PhD Program between Alibaba and Nanyang Technological University.

show abstract

UniTrans : Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data

Cited by 28 publications

References 0 publications

Target-oriented Fine-tuning for Zero-Resource Named Entity Recognition

Target-oriented Fine-tuning for Zero-Resource Named Entity Recognition

Shared Task 1 System Description : Exploring different approaches for multilingual tasks

MulDA: A Multilingual Data Augmentation Framework for Low-Resource Cross-Lingual NER

Contact Info

Product

Resources

About