The (Non-)Sense of Word Vectors (2/2)

The (Non-)Sense of Word Vectors (2/2)

This is the second part in a two-series blog. Read the first part here.

In the previous part, we discussed the differences between syntactical and semantical applications of natural language processing. In both scenarios, word vectors seem like a promising way forward given their recent popularity and success. As we outlined, word vectors work quite well on syntactical tasks given that the nature of word vectors comes from looking at words’ surroundings. For semantical applications however, we have argued that they are less suitable.

We were mainly looking to apply word vectors on sentiment analysis as a first semantical application. Our award-winning and patented RBEM algorithm is great on paper but has its flaws as it requires a vast amount of human expert input to work correctly, something we were hoping to overcome using word vectors.

Read the full article on our blog.

要查看或添加评论,请登录

Erik Tromp的更多文章

  • How Gen Z is reshaping today's job market

    How Gen Z is reshaping today's job market

    Generation Z is making its mark on the job market, transforming the employer-employee relationship as we know it. This…

  • Staffing 2.0 - Programmatic Matching

    Staffing 2.0 - Programmatic Matching

    Wow! I have been so occupied with #Personality #Match that I hardly had time to blog about it and explain to the world…

    1 条评论
  • PersonalityMatch on ProductHunt!

    PersonalityMatch on ProductHunt!

    We call it matching 2.0! Blending in personality driven by AI to make the old-fashioned recruitment and staffing…

  • Fake News Detection

    Fake News Detection

    With the recent developments of fake news playing a role in Trump’s elections, Cambridge Analytica using it to great…

  • ‘Een pakket dat geautomatiseerd bedrijven helpt’

    ‘Een pakket dat geautomatiseerd bedrijven helpt’

    Het kennen van je klant zou het uitgangspunt moeten zijn voor elk bedrijf. Met de opkomst van big data wordt het steeds…

    1 条评论
  • Deriving Personality Traits from Text

    Deriving Personality Traits from Text

    If you’d ask me, one the most compelling fields in language processing is that of authorship profiling. In this field…

  • The (Non-)Sense of Word Vectors

    The (Non-)Sense of Word Vectors

    In this new blog post we explore the power of word vectors as many claim. We show the boundaries of what they are…

  • Topic Classification – Bridging Topic Modelling and Text Classification

    Topic Classification – Bridging Topic Modelling and Text Classification

    Processing human language is a wide field with many aspects that can be of interest. One of such aspects is to find out…

  • The Need to Know Your Customer

    The Need to Know Your Customer

    The field of customer experience monitoring is a booming business, just google the term and you will be overloaded with…

    1 条评论
  • Unsupervised Deep Parsing

    Unsupervised Deep Parsing

    As I have written before, it is not always easy to understand the possibilities of current-day text analytics…

社区洞察

其他会员也浏览了