HHMM at SemEval-2019 Task 2: Unsupervised Frame Induction using Contextualized Word Embeddings
Computation and Language
2019-10-22 v1
Abstract
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.
Cite
@article{arxiv.1905.01739,
title = {HHMM at SemEval-2019 Task 2: Unsupervised Frame Induction using Contextualized Word Embeddings},
author = {Saba Anwar and Dmitry Ustalov and Nikolay Arefyev and Simone Paolo Ponzetto and Chris Biemann and Alexander Panchenko},
journal= {arXiv preprint arXiv:1905.01739},
year = {2019}
}
Comments
5 pages, 3 tables, accepted at SemEval 2019