Paper: Harvesting Parallel News Streams to Generate Paraphrases of Event Relations

ACL ID D13-1183
Title Harvesting Parallel News Streams to Generate Paraphrases of Event Relations
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2013
Authors

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 ...