Apr 22, 2014

Product attribute extraction

One of the most popular application for named entity detection is product attribute extraction. Automatically extracting product attributes from text helps E-commerce company correctly process user query and match it the right products. Marketers want to know what people are talking about related to their products. Corporate strategists wants to find out what products are trendy based on user discussions. 

Product attributes are specific properties related to a product. For example, Apple iPhone 5 with black color has 4 major attributes: Company name as “Apple”, brand name as “iPhone”, generation as “5”, color as “black”. A complete set of attributes define a product.  

What challenge do we face in extracting product attributes? We can create a dictionary of products and their corresponding attributes, but simply relying on a dictionary has its limitations:

  • A dictionary is not complete as new products are created. 
  • There is ambiguity in matching the attributes. 
  • Misspelling, abbreviations, and acronyms are used often , particularly in social media such as Twitter. 

Let’s look a case study of eBay (results were published), and see how they solve this problem. eBay is an online marketplace for sellers and buyers. Small sellers create their listings to be sold on eBay. With more than 100 million listings  on the site, sellers are selling everything from digital cameras, clothes, cars to collectibles. In order to help users quickly find an item they are interested in, eBay’s (product) search engine has to quickly match user query to existing listings. It is crucial that eBay group existing listing into products so that the search can be done quickly. This requires automatically extracting product attributes from each listing. However, they face the following challenges:

  • Each listing is less than 55 character long, which contains little context. 
  • Text is ungrammatical, with many nouns piled together.
  • Misspelling, abbreviations and acronyms occur frequently

As we can see, a dictionary-based approach does not work here due to the large volume of new listings and products on the site, and high variation in stating the same product attributes. For example, the brand “River island” has the following appearance in listings: 
river islands, river islanfd, river islan, ?river island, riverislandtop. 

How do we apply machine learning to this problem?  In a supervised learning approach, a small set of listings are labeled by humans. In each listing, each word is tagged either with an attribute name or “Other”. Different product categories have different attributes. For example, in clothing category, there are 4 major product attributes: Brand, garment type, color and size. The following is an example of a labeled listing:

                    Ann Taylor Asymmetrical  Knit Dress     NWT Red   Petite Size S
                    Brand                               Garment type          Color  Size        size

But supervised learning is very expensive as it requires a lot of labeled data. Our goal is using a small amount of labeled data and derive the rest based on bootstrapping. This is called semi-supervised learning. For detail of our semi-supervised learning approach, please see the paper in the reference. 

Duangmanee Putthividhya and Junling Hu, "Bootstrapped Named Entity Recognition for Product Attribute Extraction". EMNLP 2011: 1557-1567


  1. My partner and I stumbled over here from a different web address and thought I should check things out.
    I like what I see so i am just following you. Look forward to looking at your web page for a
    second time.

    Feel free to surf to my blog ...

  2. I actually prefer the website this one, because I like the news content that is very amazing and very useful for myself and family :)

  3. This comment has been removed by the author.

  4. This post is very information. The application which author describe in the post has many product attribute features. I think this is a useful app for users. Event planning app for ipad

  5. very informative. Big data analysis can be also applied into our SEO job. By analyzing the key words that users used to search the site, we can know what they are interested in and how to keep them interesting. BOC Sciences achieved a great progress with this method.

  6. wah artikelnya menggugah selera nih obat sakit tenggorokan saat menelan , obat kolesterol , obat batuk tbc bagus banget, sangat memotivasi dan menginspirasi

  7. thanks for sharing this with us, this is very informative article about the big data analysis.

  8. Thanks-a-mundo for the blog article.Much thanks again. Awesome.
    diwali sms images 2015

  9. Very neat article.Really looking forward to read more. Really Great.
    Prem ratan dhan payo movie torrent download

  10. Great article....
    Thanx a lot for sharing it with us...
    For tech related topics please visit my site...


  11. A big thank you for your blog.Really looking forward to read more. Fantastic.
    New year wishes 2016
    New year wishes

  12. Major thankies for the article.Really looking forward to read more. Keep writing.
    Happy new year 2016 photos, pictures
    New year greeting card images

  13. Looking forward to reading more. Great blog article.Really thank you! Cool.
    New year wishes 2016

    Happy new year wishes 2016

  14. Thanks for sharing, this is a fantastic article.Much thanks again. Really Cool.
    Happy new year quotes wishes

    new year quotes sms

    New year quotes for girlfriend

  15. This is one awesome blog article.Really looking forward to read more. Really Great.
    ride along 2 torrent download
    ride along 2 movie download

  16. Im obliged for the blog post.Really looking forward to read more. Awesome
    CBSE 12th Result

  17. I appreciate you sharing this article.Thanks Again. Much obliged.
    Holi Pictures For Facebook

  18. I really liked your blog article. Great.
    Happy Holi SMS

  19. Thanks-a-mundo for the blog post. Awesome.
    CBSE 10th Result Nic

  20. Everything is fine, am happy about your blog. Thanks admin for sharing the unique content, you have done a great job I appreciate your effort and I hope you will get more positive comments from the web users.


    SEO Training in Chennai

  21. Thanks for the great article. Click Euro Cup news to watch euro cup live

  22. About product attribute extraction given information really great,easily observe all provided information,thanks for sharing that valuable information.
    digital marketing training in chennai

    1. We made these yummy lollipops at my daughter's recent Tie-Dye Birthday party. They were a fun little treat for the girls, but they were so easy, they'd be a fun little treat to make anytime.

      one line quotes
      visit here

  23. Great information on product data. There is a lot of great work being done with product data and extraction and linking. I've come across ProductMatch by Data Ladder (, which is an excellent product attribute extraction tool used across business. They offer a complimentary trial for new users.

  24. Check out fugomo for all the latest news and gossips about bollywood


  25. this is great atikel ,, i like it,, thank for u sharing info for all people
    Situs Agen Judi Piala Eropa 2016 Terpercaya

  26. Want to know regular updates of Euro Cup 2016????
    Get Euro Cup live Streaming,Euro Cup 2016 Schedule,Euro Cup 2016 Fixture,Euro Cup 2016 Live Streaming,Euro Cup 2016 Live Stream,Euro Cup 2016 Live Score.
    Venue-France,From 10th june-10july. 24 teams,10 stadiums. Stay updated. Watch

    Wales vs Russia Live Streaming.

  27. Such simple and elegant
    Extra exquisite =) Minimal shot :-

  28. Check here to download Prisma for Android free.

  29. This application provides you all the best features for messaging which you are looking for.
    Allo app for PC

  30. Now share files from pc to smart mobile using shareit for pc for free. Shareit for PC

  31. snapdeal is now offering Various snapdeal coupons and also you can get latest deals andsnapdeal coupon codes. checkout once

  32. want to know valentines day quotes for your lover,valentines day messages,valentines day images, just checkout my site Valentines Day 2017


  34. Best New Year 2017 Wishes images for wish someone special. View our blog to see new and unique images.

  35. I would once again praise to god about this amazing post. Thank you so much for the detailed information. I love to read tips from people who are really successful with what they do. It inspires me an I learn a lot witch helps me to grow my business faster.

    Bigg Boss 10 Colors
    Big boss 10 Contestants
    Maru gujarat
    Get Venus Factor Reviews

    Thank you once again !!


  36. If Your Are Looking For Blogger Theme WordPress Themes, Plugins And Many More Just Visit Here.Free Premium Wordpress Themes And Plugins

  37. If you want to know National Cat Day 2016 and why is it celebrated by pet lovers all across the globe,
    just have a look at my blog.
    You too can celebrate this day with your loving pet cat.

  38. Want to know about Veterans Day,which is a day to celebrate the great officers of the US army,just checkout my blog Happy Veterans Day and stay updated.

  39. I would once again praise to god about this amazing post.
    Thank you so much for the detailed information.
    I love to read tips from people who are really successful with what they do.
    It inspires me an I learn a lot which helps me to grow my business faster.
    Happy Diwali Messages in Hindi
    Happy Diwali SMS in Hindi
    Happy Diwali Messages
    Happy Diwali Pictures
    Happy Diwali Whatsapp Status In Hindi
    Happy Diwali SMS 2016
    Happy Diwali Images 2016

  40. Great information..!! Product attribute extraction given information really great,and easy to understand. Thanks for sharing this great post.