"cba to check the spelling": Investigating Parser Performance on Discussion Forum Posts

We evaluate the Berkeley parser on text from an online discussion forum. We evaluate the parser output with and without gold tokens and spellings (using Sparseval and Parseval), and we compile a list of problematic phenomena for this domain. The Parseval f-score for a small development set is 77.56. This increases to 80.27 when we apply a set of simple transformations to the input sentences and to the Wall Street Journal (WSJ) training sections.

• Type: Journal
• Year: 2010
• Where: NAACL
• Authors: Jennifer Foster
• Keywords: Berkeley Parser, Computational Linguistics, NAACL 2010, Online Discussion Forum, Wall Street Journal