By applying policy-based reinforcement learning with a query
execution environment to WikiSQL, our model Seq2SQL outperforms attentional
sequence to sequence models, improving execution accuracy from 35.9% to 60.3%
and logical form accuracy from 23.4% to 49.2%.
http://m.zdnet.co.kr/news_view.asp?article_id=20170831082744#imadnews
https://www.salesforce.com/blog/2017/08/salesforce-research-ai-talk-to-data
https://github.com/salesforce/WikiSQL
https://einstein.ai/static/images/layouts/research/seq2sql/seq2sql.pdf
'머신러닝_딥러닝' 카테고리의 다른 글
| 회귀(regression)와 분류(classification) 개념 (0) | 2018.05.30 |
|---|---|
| [펌] 앙상블, 머신 러닝, 분류와 회귀 관련 랜덤 포레스트(RF) 관련 좋은 글 모음 (0) | 2018.02.07 |
| 오버 피팅(over fitting)과 언더 피팅(under fitting) (0) | 2018.02.05 |
