Differences

This shows you the differences between two versions of the page.

--- projects:fofe:start [2015/05/11 20:13] – hj
+++ projects:fofe:start [2015/08/05 06:02] (current) – hj
@@ Line 3: / Line 3: @@
 ===== Fixed-size Ordinally-Forgetting Encoding (FOFE) =====
-{{:projects:fofe:fofe_bigram2.png?0x330 |NN hidden layer}}{{ :projects:fofe:fofe_trigram.png?0x330| HOPE}}
+{{:projects:fofe:fofe_bigram2.png?0x330 |NN hidden layer}}{{ :projects:fofe:fofe_trigram.png?0x330| HOPE}} \\
-\\
-\\
+\\
 ** FOFE **
 is a simple technique to (almost) uniquely map any variable-length sequence into a fixed-size representation, which is particularly suitable for neural networks. It also has an appealing property that the far-away context will be gradually forgotten in the representation, which is good to model natural languages.
@@ Line 16: / Line 16: @@
 **Reference:**
 \\
-[1] //ShiLiang Zhang, Hui Jiang, MingBin Xu, JunFeng Hou, LiRong Dai//, "A Fixed-Size Encoding Method  for Variable-Length Sequences with its Application to Neural Network Language Models," [[http://arxiv.org/abs/1505.01504|arXiv:1505.01504]].
+[1] //S. Zhang, H. Jiang, M. Xu, J. Hou, L. Dai//, "A Fixed-Size Encoding Method  for Variable-Length Sequences with its Application to Neural Network Language Models," [[http://arxiv.org/abs/1505.01504|arXiv:1505.01504]].
+[2] //S. Zhang, H. Jiang, M. Xu, J. Hou, L. Dai//, "[[http://anthology.aclweb.org/P/P15/P15-2081.pdf|The Fixed-Size Ordinally-Forgetting Encoding Method for Neural Network Language Models]]," //Proc. of The 53th Annual Meeting of the Association for Computational Linguistics (ACL 2015)//, July 2015.
 **Software:**
 \\
-The matlab codes to reproduce the results in [1] can be downloaded here.
+The matlab codes to reproduce the results in [1,2] can be downloaded {{:projects:fofe:fofe-code.zip|here}}.