Xiaoqin Hu, Beijing Language and Culture University, China

This research aims to explore a deeper representation of the internal structure and semantic relationship of multiword nouns (MWNs) for improving MWN discovery. This representation focuses on MWN formations, which follow a series of categorical and semantic constraints. Linguistically motivated semantic features are defined by computing the internal semantic relations of MWNs. The internal structures are represented by describing categorical combinations in a hierarchy, and the internal semantic relations are represented with the help of semantic combinations of constituents. The results show that combining linguistically motivated semantic features with statistically motivated semantic features improves MWN discovery.

automatic discovery of multiword nouns, internal structure and semantic relation, categorical and semantic constraints, linguistic knowledge