BERT(s) to Detect Multiword Expressions
This work addresses a key challenge in NLP applications such as machine translation, though it is incremental as it applies existing transformer methods to a specific task.
The paper tackled the problem of detecting multiword expressions (MWEs) in natural language processing by evaluating transformer models like BERT on the DiMSUM dataset, showing they outperform previous LSTM-based neural models.
Multiword expressions (MWEs) present groups of words in which the meaning of the whole is not derived from the meaning of its parts. The task of processing MWEs is crucial in many natural language processing (NLP) applications, including machine translation and terminology extraction. Therefore, detecting MWEs is a popular research theme. In this paper, we explore state-of-the-art neural transformers in the task of detecting MWEs.We empirically evaluate several transformer models in the dataset for SemEval-2016 Task 10: Detecting Minimal Semantic Units and their Meanings (DiMSUM). We show that transformer models outperform the previous neural models based on long short-term memory (LSTM). The code and pre-trained model will be made freely available to the community.