Abstract
We propose solutions to enhance the Inside-Outside Recursive Neural Network (IORNN) reranker of Le and Zuidema (2014). Replacing the original softmax function with a hierarchical softmax using a binary tree constructed by combining output of the Brown clustering algorithm and frequency-based Huffman codes, we significantly reduce the reranker’s computational complexity. In addition, enriching contexts used in the reranker by adding subtrees rooted at (ancestors’) cousin nodes, the accuracy is increased.
Original language | English |
---|---|
Title of host publication | Proceedings of the 14th International Conference on Parsing Technologies |
Place of Publication | Bilbao, Spain |
Publisher | Association for Computational Linguistics |
Pages | 87-91 |
Number of pages | 5 |
DOIs | |
Publication status | Published - Jul 2015 |
Event | 14th International Conference on Parsing Technologies 2015 - Bilbao, Spain Duration: 22 Jul 2015 → 24 Jul 2015 |
Conference
Conference | 14th International Conference on Parsing Technologies 2015 |
---|---|
Country/Territory | Spain |
City | Bilbao |
Period | 22/07/15 → 24/07/15 |