Learning to Resolve Bridging References

We use machine learning techniques to find the best combination of local focus and lexical distance features for identifying the anchor of mereological bridging references. We find that using first mention, utterance distance, and lexical distance computed using either Google or WordNet results in an accuracy significantly higher than obtained in previous experiments.

• Type: Conference
• Year: 2004
• Where: ACL
• Authors: Massimo Poesio, Rahul Mehta, Axel Maroudas, Janet Hitzeman
• Keywords: ACL 2004, ACL 2007, Lexical Distance, Lexical Distance Features, Mereological Bridging References