Unsupervised acquisition of entailment relations from the Web. (January 2015)

• Record Type: Journal Article
• Authors: SZPEKTOR, IDAN; TANEV, HRISTO; DAGAN, IDO; COPPOLA, BONAVENTURA; KOUYLEKOV, MILEN
• Is Part Of: Natural language engineering. Volume 21:Part 1(2015)
• Page Start: 3
• Page End: 47
• Publication Date: 2015-01
• Subjects: Natural language processing (Computer science) -- Periodicals; Software engineering -- Periodicals; 006.35
• DOI: 10.1017/S1351324913000156
• Languages: English
• ISSNs: 1351-3249

Abstract

<abstract abstract-type="normal"> <title>Abstract</title> <p>Entailment recognition is a primary generic task in natural language inference, whose focus is to detect whether the meaning of one expression can be inferred from the meaning of the other. Accordingly, many NLP applications would benefit from high coverage knowledgebases of paraphrases and entailment rules. To this end, learning such knowledgebases from the Web is especially appealing due to its huge size as well as its highly heterogeneous content, allowing for a more scalable rule extraction of various domains. However, the scalability of state-of-the-art entailment rule acquisition approaches from the Web is still limited. We present a fully unsupervised learning algorithm for Web-based extraction of entailment relations. We focus on increased scalability and generality with respect to prior work, with the potential of a large-scale Web-based knowledgebase. Our algorithm takes as its input a lexical–syntactic template and searches the Web for syntactic templates that participate in an entailment relation with the input template. Experiments show promising results, achieving performance similar to a state-of-the-art unsupervised algorithm, operating over an offline corpus, but with the benefit of learning rules for different domains with no additional effort.</p> </abstract>