Data-oriented parsing (DOP, also data-oriented processing) is a probabilistic model in computational linguistics. DOP was conceived by Remko Scha in 1990 with the aim of developing a performance-oriented grammar framework. Unlike other probabilistic models, DOP takes into account all subtrees contained in a treebank rather than being restricted to, for example, 2-level subtrees (like PCFGs).
Several variants of DOP have been developed. The initial version developed by Rens Bod was based on tree-substitution grammar, while more recently, DOP has been combined with lexical-functional grammar (LFG). The resulting DOP-LFG finds an application in machine translation. Other work on learning and parameter estimation for DOP has also found its way into machine translation.
- Remko Scha Research on DOP
- DOP Homepage
- Khalil Sima'an: Learning DOP models from treebanks; Computational Complexity
- Andy Way (1999). A hybrid architecture for robust MT using LFG-DOP. Journal of Experimental and Theoretical Artificial Intelligence 11(3):441–471.