Rakuten Institute of Technology
-
Upload
rakuten-inc -
Category
Technology
-
view
214 -
download
4
Transcript of Rakuten Institute of Technology
10
Why are we working on this problem? (Key Benefits)
‣ To organize our catalog in accordance with customer
expectations
‣ To precisely search our catalog for products and its variants
‣ To measure and enforce merchant KPI's.
What are we doing? (Key Tasks)
‣ Product Genre Classification
‣ Attribute Extraction from Product Information
‣ Merchant and Item Review Analysis
How are we doing it? (Key Technologies)
‣ Large-Scale Gradient Boosted Decision Trees
‣ Deep Learning (RNN's, CNN's, others)
‣ Computing Massive Number of NLP Features
Product Catalog
Businesses
11
Each product can be assigned a category and attributes. For instance:
+Category Grocery & food
Subcategory Wine
Each (sub)category has a number of relevant attributes with a list of valid values
Challenge: this structured information is not always present or correct
Goal: automatically predict category and attributes from text and/or images
https://item.rakuten.co.jp/kawahara/345812/
12
Classifier based on
Deep Learning Algorithm (CNN)
Prec@1 92%
Prec@10 99%
Classifier based on
Deep Learning Algorithm (CNN)
Prec@1 57%
Prec@3 75%
Extracting Words
* Tested to Ichiba L3 category (1.5K categories)
* Tested for PriceMinister Image Data
Text Data
• Item Title
• Item Description
Image Data
13
我们真的很有诚意了。你说我一个老总都亲自跑了好几趟了。
Machine
translation
is A Rakuten group company which provides a video streaming service.
Volunteers are editing subtitles and translated subtitles.
https://www.viki.com/?locale=ja
14
Hobby and Entertainment
> Books and Magazine
> Business Electronics
> Audio
> Earphone / Headphone
Electronics
> Smartphone
> AC Adaptor / Battery