Parsing the LOB Corpus

This paper1 presents a rapid and robust parsing system currently used to learn from large bodies of unedited text. The system contains a multivalued part-of-speech disambiguator and a novel parser employing bottom-up recognition to nd the constituent phrases of larger structures that might be too di cult to analyze. The results of applying the disambiguator and parser to large sections of the Lancaster/ Oslo-Bergen corpus are presented.

• Type: Conference
• Year: 1990
• Where: ACL
• Authors: Carl de Marcken
• Keywords: ACL 1990, ACL 2007, Large Bodies, Multivalued Part-of-speech Disambiguator, Robust Parsing