Unsupervised Efficient Learning And Representation Of Language Structure
PROCEEDINGS OF THE TWENTY-FIFTH ANNUAL CONFERENCE OF THE COGNITIVE SCIENCE SOCIETY, PTS 1 AND 2(2003)
摘要
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络