Name
Abstract | ||
|---|---|---|
Recurrent neural language models are the state-of-the-art models for language modeling. When the vocabulary size is large, the space taken to store the model parameters becomes the bottleneck for the use of recurrent neural language models. In this paper, we introduce a simple space compression method that randomly shares the structured parameters at both the input and output embedding layers of the recurrent neural language models to significantly reduce the size of model parameters, but still compactly represent the original input and output embedding layers. The method is easy to implement and tune, Experiments on several data sets show that the new method can get similar perplexity and BLEU score results while only using a very tiny fraction of parameters. |
Year | Venue | DocType |
|---|---|---|
2018 | THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | Conference |
Volume | Citations | PageRank |
abs/1711.09873 | 0 | 0.34 |
References | Authors | |
21 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhongliang Li | 1 | 0 | 0.68 |
| Raymond Kulhanek | 2 | 0 | 0.34 |
| Shaojun Wang | 3 | 468 | 38.96 |
| Yunxin Zhao | 4 | 807 | 121.74 |
| Shuang Wu | 5 | 112 | 16.94 |