Application of natural language processing methodologies for domain specific languages, such as biomedical text, is often a challenge.

However, a more challenging aspect of processing data in these domains is that they do not sample all of the available knowledge space.

In this talk, I will summarize our recent work that aims to address the “needle in a haystack” problem. I will also briefly describe how our collaborative NLP platform not only powers use case delivery but also drives our research interests forward.