Static and Dynamic Feature Selection in Morphosyntactic Analyzers
This work addresses efficiency and accuracy improvements in morphosyntactic tagging for multiple languages, representing an incremental advance with specific gains.
The paper tackled feature selection in morphosyntactic analyzers by comparing static and dynamic ordering methods, showing that dynamic ordering improves accuracy and reduces model size and runtime by up to 80% in some cases.
We study the use of greedy feature selection methods for morphosyntactic tagging under a number of different conditions. We compare a static ordering of features to a dynamic ordering based on mutual information statistics, and we apply the techniques to standalone taggers as well as joint systems for tagging and parsing. Experiments on five languages show that feature selection can result in more compact models as well as higher accuracy under all conditions, but also that a dynamic ordering works better than a static ordering and that joint systems benefit more than standalone taggers. We also show that the same techniques can be used to select which morphosyntactic categories to predict in order to maximize syntactic accuracy in a joint system. Our final results represent a substantial improvement of the state of the art for several languages, while at the same time reducing both the number of features and the running time by up to 80% in some cases.