Natural Language Processing (NLP) is an essential part of a growing number of products, covering a vast scope of issues from the seemingly mundane (entity recognition) to the seriously involved (automatic summarization). In all cases, the goal is to reproduce or approximate a process - language - that we as humans rarely think twice about: this makes NLP a field fraught with misunderstandings and incorrect assumptions.

We will talk about the common pitfalls of treating language like 'just another data-set’ and offer some insight into best practices.