TIIS (한국인터넷정보학회)
Current Result Document : 6 / 8
| 한글제목(Korean Title) |
Robustness of Differentiable Neural Computer Using Limited Retention Vectorbased Memory Deallocation in Language Model |
| 영문제목(English Title) |
Robustness of Differentiable Neural Computer Using Limited Retention Vectorbased Memory Deallocation in Language Model |
| 저자(Author) |
Donghyun Lee
Hosung Park
Soonshin Seo
Hyunsoo Son
Gyujin Kim
and Ji-Hwan Kim
|
| 원문수록처(Citation) |
VOL 15 NO. 03 PP. 0837 ~ 0852 (2021. 03) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
Recurrent neural network (RNN) architectures have been used for language modeling (LM) tasks that require learning long-range word or character sequences. However, the RNN architecture is still suffered from unstable gradients on long-range sequences. To address the issue of long-range sequences, an attention mechanism has been used, showing state-of-theart (SOTA) performance in all LM tasks. A differentiable neural computer (DNC) is a deep learning architecture using an attention mechanism. The DNC architecture is a neural network augmented with a content-addressable external memory. However, in the write operation, some information unrelated to the input word remains in memory. Moreover, DNCs have been found to perform poorly with low numbers of weight parameters. Therefore, we propose a robust memory deallocation method using a limited retention vector. The limited retention vector determines whether the network increases or decreases its usage of information in external memory according to a threshold. We experimentally evaluate the robustness of a DNC implementing the proposed approach according to the size of the controller and external memory on the enwik8 LM task. When we decreased the number of weight parameters by 32.47%, the proposed DNC showed a low bits-per-character (BPC) degradation of 4.30%, demonstrating the effectiveness of our approach in language modeling tasks.
|
| 키워드(Keyword) |
Differentiable Neural Computer (DNC)
Language Model (LM)
Memory Deallocation
Retention Vector
Robustness
|
| 파일첨부 |
PDF 다운로드
|
