Unsupervised Semantic Frame Induction using Triclustering
Computation and Language
2019-10-22 v2
Abstract
We use dependency triples automatically extracted from a Web-scale corpus to perform unsupervised semantic frame induction. We cast the frame induction problem as a triclustering problem that is a generalization of clustering for triadic data. Our replicable benchmarks demonstrate that the proposed graph-based approach, Triframes, shows state-of-the art results on this task on a FrameNet-derived dataset and performing on par with competitive methods on a verb class clustering task.
Keywords
Cite
@article{arxiv.1805.04715,
title = {Unsupervised Semantic Frame Induction using Triclustering},
author = {Dmitry Ustalov and Alexander Panchenko and Andrei Kutuzov and Chris Biemann and Simone Paolo Ponzetto},
journal= {arXiv preprint arXiv:1805.04715},
year = {2019}
}
Comments
8 pages, 1 figure, 4 tables, accepted at ACL 2018