Incremental Dependency Parsing Using Online Learning

We describe an incremental parser that was trained to minimize cost over sentences rather than over individual parsing actions. This is an attempt to use the advantages of the two top-scoring systems in the CoNLL-X shared task. In the evaluation, we present the performance of the parser in the Multilingual task, as well as an evaluation of the contribution of bidirectional parsing and beam search to the parsing performance.

• Type: Conference
• Year: 2007
• Where: EMNLP
• Authors: Richard Johansson, Pierre Nugues
• Keywords: CoNLL-X Shared Task, EMNLP 2007, Individual Parsing Actions, Natural Language Processing, Parsing