Unsupervised efficient learning and representation of language structure
Unsupervised efficient learning and representation of language structure Proceedings of the 25th Annual Cognitive Science Society, 1106-1109
Authors
Z Solan, D Horn, E Ruppin, S Edelman
Abstract
We describe a linguistic pattern acquisition algorithm that learns, in an unsupervised fashion, a streamlined representation of corpus data. This is achieved by compactly coding recursively structured constituent patterns, and by placing strings that have an identical backbone and similar context structure into the same equivalence class. The resulting representations constitute an efficient encoding of linguistic knowledge and support systematic generalization to unseen sentences.