论文信息 - Automatic Extraction of Hypernyms and Hyponyms from Russian Texts

Automatic Extraction of Hypernyms and Hyponyms from Russian Texts

The paper describes a rule-based approach for hypernym and hyponym extraction from Russian texts. For this task we employ finite state transducers (FSTs). We developed 6 finite state transducers that encode 6 lexicosyntactic patterns, which show a good precision on Russian DBpedia: 79.5% of the matched contexts are correct.

Artem Lukanin | Kristina Sabirova

[1] Daniel Jurafsky,et al. Learning Syntactic Patterns for Automatic Hypernym Discovery , 2004, NIPS.

[2] Oren Etzioni,et al. What Is This, Anyway: Automatic Hypernym Discovery , 2009, AAAI Spring Symposium: Learning by Reading and Learning to Read.

[3] Irina V. Azarowa. RussNet as a Computer Lexicon for Russian , 2008 .

[4] Marti A. Hearst. Automatic Acquisition of Hyponyms from Large Text Corpora , 1992, COLING.

[5] P. Bell,et al. In the beginning... , 2011, European journal of vascular and endovascular surgery : the official journal of the European Society for Vascular Surgery.

[6] Michael P. Oakes. Using Hearst's Rules for the Automatic Acquisition of Hyponyms for Mining a Pharmaceutical Corpus , 2005, RANLP Text Mining Workshop.

[7] Antonio Sanfilippo,et al. The Acquisition of Lexical Knowledge from Combined Machine-Readable Dictionary Sources , 1992, ANLP.

[8] Alexander Panchenko,et al. A semantic similarity measure based on lexico-syntactic patterns , 2012, KONVENS.

[9] Sharon A. Caraballo. Automatic construction of a hypernym-labeled noun hierarchy from text , 1999, ACL.

[10] Lucy Vanderwende,et al. Automatically Deriving Structured Knowledge Bases From On-Line Dictionaries , 1993 .

[11] Xabier Arregi,et al. Extraction of semantic relations from a Basque monolingual dictionary using Constraint Grammar , 2000, ArXiv.