Big Data Methods for Computational Linguistics

Many tasks in computational linguistics traditionally rely on hand-crafted or curated resources like thesauri or word-sense-annotated corpora. The availability of big data, from the Web and other sources, has changed this situation. Harnessing these assets requires scalable methods for data and text analytics. This paper gives an overview on our recent work that utilizes big data methods for enhancing semantics-centric tasks dealing with natural language texts. We demonstrate a virtuous cycle in harvesting knowledge from large data and text collections and leveraging this knowledge in order to improve the annotation and interpretation of language in Web pages and social media. Specifically, we show how to build large dictionaries of names and paraphrases for entities and relations, and how these help to disambiguate entity mentions in texts.