id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_rm5frn4rmvawvklaxkaojqxb6a	Congle Zhang	Exploiting Parallel News Streams for Unsupervised Event Extraction	2015	14	.pdf	application/pdf	9154	827	67	graphical model to cluster sentences describing similar events from parallel news streams. NEWSSPIKE-RE generates high quality training sentences and learns extractors that perform much better than rival approaches, more which can achieve high precision and recall, are limited by the cost of labeling training data and are unlikely to scale to the thousands of relations on the This paper develops a new unsupervised technique, NEWSSPIKE-RE, to both discover event relations and extract them with high precision. • We develop a method to discover a set of distinct, salient event relations from news streams. • We describe an algorithm to exploit parallel news streams to cluster sentences that belong to the same event relations. phase has two main steps: event-relation discovery and training-set generation. our event relation discovery algorithm, which processes time-stamped news articles to discern a set model, described in Section 5.2, to accurately assign sentences from NewsSpikes to each discovered event relation E.	./cache/work_rm5frn4rmvawvklaxkaojqxb6a.pdf	./txt/work_rm5frn4rmvawvklaxkaojqxb6a.txt