Abstract | ||
---|---|---|
Pattern-based methods of IS-A relation extraction rely heavily on so called Hearst patterns. These are ways of expressing instance enumerations of a class in natural language. While these lexico-syntactic patterns prove quite useful, they may not capture all taxonomical relations expressed in text. Therefore in this paper we describe a novel method of IS-A relation extraction from patterns, which uses morpho-syntactical annotations along with grammatical case of noun phrases that constitute entities participating in IS-A relation. We also describe a method for increasing the number of extracted relations that we call pseudosubclass boosting which has potential application in any pattern-based relation extraction method. Experiments were conducted on a corpus of about 0.5 billion web documents in Polish language. |
Year | DOI | Venue |
---|---|---|
2016 | 10.15439/2016F391 | 2016 Federated Conference on Computer Science and Information Systems (FedCSIS) |
Keywords | DocType | Volume |
grammatical case,IS-A relation extraction,Polish language,Hearst patterns,instance enumerations,natural language,lexico-syntactic patterns,taxonomical relations,morpho-syntactical annotations,noun phrases,pseudosubclass boosting,pattern-based relation extraction | Conference | abs/1605.02916 |
ISSN | ISBN | Citations |
2300-5963 | 978-1-5090-0046-3 | 0 |
PageRank | References | Authors |
0.34 | 16 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pawel Lozinski | 1 | 0 | 0.34 |
Dariusz Czerski | 2 | 5 | 3.97 |
Mieczyslaw A. Klopotek | 3 | 366 | 78.58 |