Hierarchical Meta-Embeddings for Code-Switching Named Entity Recognition

TL;DR

This paper introduces Hierarchical Meta-Embeddings, a novel method combining monolingual word and subword embeddings to improve code-switching Named Entity Recognition, achieving state-of-the-art results.

Contribution

The paper proposes Hierarchical Meta-Embeddings that effectively integrate multiple language-specific embeddings for better code-switching NER performance.

Findings

Achieves state-of-the-art results on English-Spanish code-switching NER

Leverages both related and unrelated languages in cross-lingual settings

Combining subunits is crucial for capturing code-switching entities

Abstract

In countries that speak multiple main languages, mixing up different languages within a conversation is commonly called code-switching. Previous works addressing this challenge mainly focused on word-level aspects such as word embeddings. However, in many cases, languages share common subwords, especially for closely related languages, but also for languages that are seemingly irrelevant. Therefore, we propose Hierarchical Meta-Embeddings (HME) that learn to combine multiple monolingual word-level and subword-level embeddings to create language-agnostic lexical representations. On the task of Named Entity Recognition for English-Spanish code-switching data, our model achieves the state-of-the-art performance in the multilingual settings. We also show that, in cross-lingual settings, our model not only leverages closely related languages, but also learns from languages with different roots. Finally, we show that combining different subunits are crucial for capturing code-switching entities.