Character n-Gram embeddings to improve RNN language models

Sho Takase, Jun Suzuki, Masaaki Nagata

研究成果: Conference contribution

10 被引用数 (Scopus)

抄録

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 ngram 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.

本文言語English
ホスト出版物のタイトル33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019
出版社AAAI Press
ページ5074-5082
ページ数9
ISBN(電子版)9781577358091
出版ステータスPublished - 2019
イベント33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Annual Conference on Innovative Applications of Artificial Intelligence, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019 - Honolulu, United States
継続期間: 2019 1月 272019 2月 1

出版物シリーズ

名前33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019

Conference

Conference33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Annual Conference on Innovative Applications of Artificial Intelligence, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019
国/地域United States
CityHonolulu
Period19/1/2719/2/1

ASJC Scopus subject areas

  • 人工知能

フィンガープリント

「Character n-Gram embeddings to improve RNN language models」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル