Weakly Supervised Cross-Lingual Named Entity Recognition via Effective Annotation and Representation Projection

Abstract

The state-of-the-art named entity recognition (NER) systems are supervised machine learning models that require large amounts of manually annotated data to achieve high accuracy. However, annotating NER data by human is expensive and time-consuming, and can be quite difficult for a new language. In this paper, we present two weakly supervised approaches for cross-lingual NER with no human annotation in a target language. The first approach is to create automatically labeled NER data for a target language via annotation projection on comparable corpora, where we develop a heuristic scheme that effectively selects good-quality projection-labeled data from noisy data. The second approach is to project distributed representations of words (word embeddings) from a target language to a source language, so that the source-language NER system can be applied to the target language without re-training. We also design two co-decoding schemes that effectively combine the outputs of the two projection-based approaches. We evaluate the performance of the proposed approaches on both in-house and open NER data for several target languages. The results show that the combined systems outperform three other weakly supervised approaches on the CoNLL data.

11 pages, The 55th Annual Meeting of the Association for Computational Linguistics (ACL), 2017

Cited by in corpus (37)

• Towards Lingua Franca Named Entity Recognition with BERT
• Exploring Fine-tuning Techniques for Pre-trained Cross-lingual Models via Continual Learning
• Cross-Lingual Named Entity Recognition Using Parallel Corpus: A New Approach Using XLM-RoBERTa Alignment
• Attention-Informed Mixed-Language Training for Zero-shot Cross-lingual Task-oriented Dialogue Systems
• Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning
• Neural Cross-Lingual Named Entity Recognition with Minimal Resources
• Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language
• A Robust and Domain-Adaptive Approach for Low-Resource Named Entity Recognition
• End-to-End Slot Alignment and Recognition for Cross-Lingual NLU
• Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resources
• Multi-Source Cross-Lingual Model Transfer: Learning What to Share
• Cross-Lingual Relation Extraction with Transformers
• Reinforced Iterative Knowledge Distillation for Cross-Lingual Named Entity Recognition
• UniTrans: Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data
• Adversarial Learning with Contextual Embeddings for Zero-resource Cross-lingual Classification and NER
• Modality-Transferable Emotion Embeddings for Low-Resource Multimodal Emotion Recognition
• Low-Resource Name Tagging Learned with Weakly Labeled Data
• AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER
• A Rigorous Study on Named Entity Recognition: Can Fine-tuning Pretrained Model Lead to the Promised Land?
• XL-NBT: A Cross-lingual Neural Belief Tracking Framework
• Entity Projection via Machine Translation for Cross-Lingual NER
• CalibreNet: Calibration Networks for Multilingual Sequence Labeling
• Cross-Lingual Vision-Language Navigation
• Low-Resource Sequence Labeling via Unsupervised Multilingual Contextualized Representations
• Why Overfitting Isn't Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionaries
• X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing
• Coarse-to-Fine Pre-training for Named Entity Recognition
• Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training
• LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning from Explanation
• What Matters for Neural Cross-Lingual Named Entity Recognition: An Empirical Analysis
• Cross-Lingual Transfer for Distantly Supervised and Low-resources Indonesian NER
• Converse Attention Knowledge Transfer for Low-Resource Named Entity Recognition
• Neural Cross-Lingual Coreference Resolution and its Application to Entity Linking
• Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Filling
• XLEnt: Mining a Large Cross-lingual Entity Dataset with Lexical-Semantic-Phonetic Word Alignment
• Open Named Entity Modeling from Embedding Distribution
• AdaK-NER: An Adaptive Top-K Approach for Named Entity Recognition with Incomplete Annotations