Harvesting Parallel News Streams to Generate Paraphrases of Event Relations

Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1776–1786, Seattle, Washington, USA, 18-21 October 2013. c⃝2013 Association for Computational Linguistics Harvesting Parallel News Streams to Generate Paraphrases of Event Relations Congle Zhang, Daniel S. Weld Computer Science & Engineering University of Washington Seattle, WA 98195, USA {clzhang,weld}@cs.washington.edu Abstract The distributional hypothesis, which states that words that occur in similar contexts tend to have similar meanings, has inspired sev- eral Web mining algorithms for paraphras- ing semantically equivalent phrases. Unfortu- nately, these methods have several drawbacks, such as confusing synonyms with antonyms and causes with effects. This paper intro- duces three Temporal Correspondence Heuris- tics, that characterize regularities in parallel news streams, and shows how they may be used to generate high precision paraphrases for event relations. We encode the heuristics in a probabilistic graphical model to create the NEWSSPIKE algorithm for mining news streams. We present experiments demon- strating that NEWSSPIKE significantly outper- forms several competitive baselines. In order to spur further research, we provide a large annotated corpus of timestamped news arti- cles as well as the paraphrases produced by NEWSSPIKE. 1 Introduction Paraphrasing, the task of finding sets of semantically equivalent surface forms, is crucial to many natu- ral language processing applications, including re- lation extraction (Bhagat and Ravichandran, 2008), question answering (Fader et al., 2013), summa- rization (Barzilay et al., 1999) and machine transla- tion (Callison-Burch et al., 2006). While the benefits of paraphrasing have been demonstrated, creating a large-scale corpus of high precision paraphrases re- mains a challenge — especially for event relations. Many researchers have considered generating paraphrases by mining the Web guided by the dis- tributional hypothesis, which states that words oc- curring in similar contexts tend to have similar meanings (Harris, 1954). For example, DIRT (Lin and Pantel, 2001) and Resolver (Yates and Etzioni, 2009) identify synonymous relation phrases by the distributions of their arguments. However, the dis- tributional hypothesis has several drawbacks. First, it can confuse antonyms with synonyms because antonymous phrases appear in similar contexts as of- ten as synonymous phrases. For the same reasons, it also often confuses causes with effects. For exam- ple, DIRT reports that the closest phrase to fall is rise, and the closest phrase to shoot is kill.1 Sec- ond, the distributional hypothesis relies on statis- tics over large corpora to produce accurate similarity statistics. It remains unclear how to accurately para- phrase less frequent relations with the distributional hypothesis. Another common approach employs the use of parallel corpora. News articles are an interesting target, because there often exist articles from dif- ferent sources describing the same daily events. This peculiar property allows the use of the tem- poral assumption, which assumes that phrases in articles published at the same time tend to have similar meanings. For example, the approaches by Dolan et al. (2004) and Barzilay et al. (2003) iden- tify pairs of sentential paraphrases in similar arti- cles that have appeared in the same period of time. While these …

Content truncated to 500 words