Bilingual Character Representation for Efficiently Addressing Out-of-Vocabulary Words in Code-Switching Named Entity Recognition
This addresses the challenge of processing noisy, multilingual social media text for NLP applications, but it is incremental as it builds on existing methods for a specific domain.
The authors tackled the problem of named entity recognition in code-switching Twitter data by proposing an LSTM-based model with bilingual character representation and transfer learning to handle out-of-vocabulary words, achieving a 62.76% harmonic mean F1-score in a shared task.
We propose an LSTM-based model with hierarchical architecture on named entity recognition from code-switching Twitter data. Our model uses bilingual character representation and transfer learning to address out-of-vocabulary words. In order to mitigate data noise, we propose to use token replacement and normalization. In the 3rd Workshop on Computational Approaches to Linguistic Code-Switching Shared Task, we achieved second place with 62.76% harmonic mean F1-score for English-Spanish language pair without using any gazetteer and knowledge-based information.