Frustratingly Hard Domain Adaptation for Dependency Parsing

We describe some challenges of adaptation in the 2007 CoNLL Shared Task on Domain Adaptation. Our error analysis for this task suggests that a primary source of error is differences in annotation guidelines between treebanks. Our suspicions are supported by the observation that no team was able to improve target domain performance substantially over a state of the art baseline.

• Type: Conference
• Year: 2007
• Where: EMNLP
• Authors: Mark Dredze, John Blitzer, Partha Pratim Talukdar, Kuzman Ganchev, João Graça, Fernando Pereira
• Keywords: CoNLL Shared Task, Domain Adaptation, EMNLP 2007, Error Analysis, Natural Language Processing