Paper: What’s in a Preposition? Dimensions of Sense Disambiguation for an Interesting Word Class

ACL ID C10-2052
Title What’s in a Preposition? Dimensions of Sense Disambiguation for an Interesting Word Class
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010
Authors

Choosing the right parameters for a word sense disambiguation task is critical to the success of the experiments. We ex- plore this idea for prepositions, an of- ten overlooked word class. We examine the parameters that must be considered in preposition disambiguation, namely con- text, features, and granularity. Doing so delivers an increased performance that significantly improves over two state-of- the-art systems, and shows potential for improving other word sense disambigua- tion tasks. We report accuracies of 91.8% and 84.8% for coarse and fine-grained preposition sense disambiguation, respec- tively.