Product

Semantic Labeling added to the Text Analysis Add-on

Semantic Labeling is a very popular feature with our Text API users, so we’ve decided to roll it out, as a fully functional Text Analysis Add-on feature too.

For this blog we’re going to walk you through what it does and use some examples to showcase how useful it can be for classifying or categorizing text.

So what exactly is Semantic Labeling?

It’s an intelligent way of tagging or categorizing text, based on labels that you suggest. It’s a training-less approach to classification, which means, it doesn’t rely on a predefined taxonomy to categorize or tag textual content.

With Semantic Labeling you can provide a piece of text, specify a set of labels and the add-on will automatically assign the most appropriate label to that text. This allows for greater flexibility for add-on users to decide how they want to tag and categorize text in their spreadsheets

Our customers are using this feature for a variety of different use cases. We’ll walk you through a couple of simple ones, to show you the feature in action.

Text Classification from a URL

Say for example, I run a sports blog and I want to automatically curate and categorize lots of articles/URL’s into predefined categories that I cover on my blog and list them in a spreadsheet.

Any of the features in the add-on can be used to analyze a URL. Just choose the cell containing that URL in your spreadsheet and hit analyze. Using the Semantic Labeling feature is a little different because you need to also submit your candidate labels through the Text Analysis Add-on sidebar.

Once you choose Semantic Labeling, you’ll notice 5 label options will populate on the right. This is where you enter your categories or labels. In this case, we’re going to use the following URL and Labels.

Example URL:

http://insider.espn.go.com/nfl/story/_/id/12300361/bold-move-new-england-patriots-miami-dolphins-new-york-jets-buffalo-bills-nfl

Labels:

  • Golf
  • Football
  • Soccer
  • Hockey
  • Cricket
     
    Once you’ve selected the cell that you want to analyze and you’ve entered your labels, just hit analyze.

    The add-on will then populate the results in the next 5-10 cells in that row. As is the case in the example below.

    In this case the add-on chose “Football”, as the most closely related label to the article on that webpage. The add-on also displays a confidence score showing which label is “the winner”.

    As you can see from the screenshot of the URL below it did a pretty nice job of recognizing the article had nothing to do with soccer or golf and was primarily about Football.

    Article Screenshot:

    Customer Query Routing

    We’ve also seen our users analyze social interactions like Tweets, Facebook comments and even Email to try and intelligently understand and tag them without the need for manual reading.

    So, let’s say we want to automatically determine whether a post on social media should be routed to and dealt with by our Sales, Support or Finance Departments.

    We’ll use 2 different Tweets that could be handled by different teams within a business and use the different department titles as labels.

    Labels:

  • Sales
  • Finance
  • Support
     
    Tweets:
  • “Are you guys down? I can’t access my account?”
  • “Who do I get in touch with if I want purchase your software?”
     
    Again, choose the cells you want to analyze that contain your Tweets, add your candidate labels in the sidebar and hit analyze.

    The add-on, as shown in the previous example, will populate it’s results in the next few cells showing the most appropriate label first, along with it’s score.

    Again the add-on was pretty accurate in assigning the correct labels to each Tweet. The first Tweet was tagged as most relevant to support and the second one was most appropriately referred to the sales department.

    This feature allows you to analyze and categorize long and short form text based off your own labels or tags. You can submit between 2 and 5 labels to the add-on and it will return the most semantically relevant tag as well as a confidence score.





  • Text Analysis API - Sign up




    Author


    Avatar

    Parsa Ghaffari

    CEO and Founder of AYLIEN Parsa is an AI, Machine Learning and NLP enthusiast, whose aim is to make these techniques and technologies more accessible and easier to use for developers and data scientists. When he’s not working he likes to play chess ('parsabg' on lichess.org). Twitter: @parsaghaffari