Name
Abstract | ||
|---|---|---|
This paper proposes a novel Recurrent Neural Network (RNN) language model that takes advantage of character information. We focus on character n-grams based on research in the field of word embedding construction (Wieting et al. 2016). Our proposed method constructs word embeddings from character n-gram embeddings and combines them with ordinary word embeddings. We demonstrate that the proposed method achieves the best perplexities on the language modeling datasets: Penn Treebank, WikiText-2, and WikiText-103. Moreover, we conduct experiments on application tasks: machine translation and headline generation. The experimental results indicate that our proposed method also positively affects these tasks. |
Year | Venue | Field |
|---|---|---|
2019 | THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | Headline,Computer science,Machine translation,Recurrent neural network,Treebank,n-gram,Natural language processing,Artificial intelligence,Word embedding,Language model,Machine learning |
DocType | Citations | PageRank |
Journal | 0 | 0.34 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sho Takase | 1 | 28 | 10.23 |
| Junichi Suzuki | 2 | 1265 | 112.15 |
| Masaaki Nagata | 3 | 19 | 5.41 |