FAME: Feature-Based Adversarial Meta-Embeddings for Robust Input Representations
This work addresses the problem of robust input representation for NLP practitioners, particularly in low-resource settings, by improving embedding combination methods, though it is incremental as it builds on existing meta-embedding approaches.
The paper tackles the challenge of combining different types and dimensions of embeddings for NLP tasks by proposing FAME, a feature-based adversarial meta-embedding method that uses word-specific features and adversarial training, resulting in state-of-the-art performance for POS tagging in 27 languages, NER, and question classification.
Combining several embeddings typically improves performance in downstream tasks as different embeddings encode different information. It has been shown that even models using embeddings from transformers still benefit from the inclusion of standard word embeddings. However, the combination of embeddings of different types and dimensions is challenging. As an alternative to attention-based meta-embeddings, we propose feature-based adversarial meta-embeddings (FAME) with an attention function that is guided by features reflecting word-specific properties, such as shape and frequency, and show that this is beneficial to handle subword-based embeddings. In addition, FAME uses adversarial training to optimize the mappings of differently-sized embeddings to the same space. We demonstrate that FAME works effectively across languages and domains for sequence labeling and sentence classification, in particular in low-resource settings. FAME sets the new state of the art for POS tagging in 27 languages, various NER settings and question classification in different domains.