HHMM at SemEval-2019 Task 2: Unsupervised Frame Induction using Contextualized Word Embeddings
This work addresses semantic frame induction for natural language processing, presenting an incremental improvement with competitive results.
The paper tackled unsupervised semantic frame induction by separating it into verb clustering and role labeling steps, achieving the best performance in Subtask B.1 and runner-up in Subtask A at SemEval 2019 Task 2.
We present our system for semantic frame induction that showed the best performance in Subtask B.1 and finished as the runner-up in Subtask A of the SemEval 2019 Task 2 on unsupervised semantic frame induction (QasemiZadeh et al., 2019). Our approach separates this task into two independent steps: verb clustering using word and their context embeddings and role labeling by combining these embeddings with syntactical features. A simple combination of these steps shows very competitive results and can be extended to process other datasets and languages.