We develop a probabilistic latent-variable model to discover semantic frames---types of events and their participants---from corpora. We present a Dirichlet-multinomial model in which frames are latent categories that explain the linking of verb-subject-object triples, given document-level sparsity. We analyze what the model learns, and compare it to FrameNet, noting it learns some novel and interesting frames. This document also contains a discussion of inference issues, including concentration parameter learning; and a small-scale error analysis of syntactic parsing accuracy.
@article{arxiv.1307.7382,
title = {Learning Frames from Text with an Unsupervised Latent Variable Model},
author = {Brendan O'Connor},
journal= {arXiv preprint arXiv:1307.7382},
year = {2013}
}
Comments
21 pages; technical report for Data Analysis Project requirement, Machine Learning Department, Carnegie Mellon University