BERT for Monolingual and Cross-Lingual Reverse Dictionary
This addresses the problem of efficient word retrieval from descriptions for monolingual and cross-lingual applications, with incremental improvements in method adaptation.
The paper tackled the reverse dictionary task, where a target word is found from its description, by adapting BERT to generate words despite its subword encoding, and extended it to cross-lingual settings using Multilingual BERT without needing parallel data, achieving remarkable performance.
Reverse dictionary is the task to find the proper target word given the word description. In this paper, we tried to incorporate BERT into this task. However, since BERT is based on the byte-pair-encoding (BPE) subword encoding, it is nontrivial to make BERT generate a word given the description. We propose a simple but effective method to make BERT generate the target word for this specific task. Besides, the cross-lingual reverse dictionary is the task to find the proper target word described in another language. Previous models have to keep two different word embeddings and learn to align these embeddings. Nevertheless, by using the Multilingual BERT (mBERT), we can efficiently conduct the cross-lingual reverse dictionary with one subword embedding, and the alignment between languages is not necessary. More importantly, mBERT can achieve remarkable cross-lingual reverse dictionary performance even without the parallel corpus, which means it can conduct the cross-lingual reverse dictionary with only corresponding monolingual data. Code is publicly available at https://github.com/yhcc/BertForRD.git.