Multilinguals at SemEval-2022 Task 11: Complex NER in Semantically Ambiguous Settings for Low Resource Languages
Not on the map. Why?
Abstract (arXiv)
We leverage pre-trained language models to solve the task of complex NER for two low-resource languages: Chinese and Spanish. We use the technique of Whole Word Masking(WWM) to boost the performance of masked language modeling objective on large and unsupervised corpora. We experiment with multiple neural network architectures, incorporating CRF, BiLSTMs, and Linear Classifiers on top of a fine-tuned BERT layer. All our models outperform the baseline by a significant margin and our best performing model obtains a competitive position on the evaluation leaderboard for the blind test set.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 19 of its 28 references that are in the map. First posted on arXiv 14 Jul 2022.
Builds on
19 of 28 references.
References · 19
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
- 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,475
- 2016Neural Architectures for Named Entity Recognitioncited by 550
- 2015Bidirectional LSTM-CRF Models for Sequence Taggingcited by 546
- 2020LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentioncited by 326
- 2020Revisiting Pre-Trained Models for Chinese Natural Language Processingcited by 266
- 2020Automated Concatenation of Embeddings for Structured Predictioncited by 86
- 2021Improving Named Entity Recognition by External Context Retrieving and Cooperative Learningcited by 76
- 2020FLERT: Document-Level Features for Named Entity Recognitioncited by 45
- 2018Neural Cross-Lingual Named Entity Recognition with Minimal Resourcescited by 44
- 2019Cloze-driven Pretraining of Self-attention Networkscited by 41
7 more
- 2021Learning from Noisy Labels for Entity-Centric Information Extractioncited by 34
- 2020Exploring Cross-sentence Contexts for Named Entity Recognition with BERTcited by 27
- 2020Soft Gazetteers for Low-Resource Named Entity Recognitioncited by 20
- 2019Zero-Resource Cross-Lingual Named Entity Recognitioncited by 18
- 2021ANEA: Distant Supervision for Low-Resource Named Entity Recognitioncited by 8
- 2019Massively Multilingual Transfer for NERcited by 2
- 2020Detecting Potential Topics In News Using BERT, CRF and Wikipediacited by 1
Built on by
Citing papers per year: 2023: 1.
1 paper.