Year: 2004
Type: conference-paper
Abstract: We present an investigation into parsing the Penn Chinese Treebank using a Data-Oriented Parsing (DOP) approach. DOP\ncomprises an experience-based approach to natural language parsing. Most published research in the DOP framework uses PStrees as its representation schema. Drawbacks of the DOP approach centre around issues of efficiency. We incorporate recent advances in DOP parsing techniques into a novel DOP parser which generates a compact representation of all subtrees which can be derived from any full parse tree.\nWe compare our work to previous work on parsing the Penn Chinese Treebank, and provide both a quantitative and qualitative evaluation. While our results in terms of Precision and Recall are slightly below those published in related research, our approach requires no manual encoding of head rules, nor is a development phase per se necessary.\nWe also note that certain constructions which were problematic in this previous work can be handled correctly by our DOP parser. Finally, we observe that the ‘DOP Hypothesis’ is confirmed for parsing the Penn Chinese Treebank.
Authors: Mary Hearne, Andy Way
Institution: Dublin City University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W28706907