Yves Peirsman is an NLP Consultant at NLP Town. He holds an MSc in Speech & Language Processing from the University of Edinburgh, a PhD in Computational Linguistics from the University of Leuven and was a post-doctoral researcher in the NLP group at Stanford University. After a few years as an NLP engineer at Textkernel and Wolters Kluwer, he became active as an NLP consultant in 2014. Since then he has contributed to various NLP projects, in fields such as machine translation, semantic search and text generation.
Between Custom and Off-the-shelf NLP
In recent years, Natural Language Processing seems to have become somewhat of a commodity. Cloud APIs such as TextRazor, Aylien and AlchemyAPI offer off-the-shelf NLP solutions such as entity recognition and sentiment analysis in a variety of languages. NLP software packages such as SpaCy (Python) and Stanford CoreNLP (Java) allow developers to integrate various NLP tasks directly into their own software, with or without modification. Libraries such as scikit-learn (for a wide variety of machine learning models) and TensorFlow (for neural networks) significantly lower the threshold for developers to enter into machine learning and build their own NLP models. In this fragmented landscape, it can be hard to see the forest for the trees. In this presentation, I will explore the continuum between custom and off-the-shelf NLP. I will review the landscape of NLP APIs and libraries and evaluate if these tools really deliver on their promises. Finally, I will give recommendations about how to pick and choose from the available options and how to build a high-performing NLP solution.