[2006.14223] Neural Machine Translation For Paraphrase Generationopen searchopen navigation menucontact arXivsubscribe to arXiv mailings

Training a spoken language understanding system, as the one in Alexa, typically requires a large human-annotated corpus of data. Manual annotations are expensive and time consuming. In Alexa Skill Kit (ASK) user experience with the skill greatly depends on the amount of data provided by skill developer. In this work, we present an automatic natural language generation system, capable of generating both human-like interactions and annotations by the means of paraphrasing. Our approach consists of machine translation (MT) inspired encoder-decoder deep recurrent neural network. We evaluate our model on the impact it has on ASK skill, intent, named entity classification accuracy and sentence level coverage, all of which demonstrate significant improvements for unseen skills on natural language understanding (NLU) models, trained on the data augmented with paraphrases.

Date: 2020/06/27 15:51

Related Entries

Read more [2006.16668] GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingopen se...
0 users, 7 mentions 2020/07/01 02:21
Read more グリーンバック不要で前景を精密に抜き出す、深層学習を用いたAlpha Matting技術「HAttMatting」 | Seamless
53 users, 20 mentions 2020/07/03 23:18
Read more 2020年 7月 4日「G検定」200問 振り返り|カオカオ
1 users, 1 mentions 2020/07/06 05:21
Read more 異常検知専用の画像認識アルゴリズム「DAGAN」を開発!(AI×製造)【論文】 | アイブン
0 users, 5 mentions 2020/07/06 22:00
Read more Social Implementation of Machine Learning - Speaker Deck
24 users, 19 mentions 2020/07/10 09:51