Our Interaction and Analytics Lab is offering a position for an on-going project that requires the extraction of knowledge from unstructured documents using modeling and techniques from Natural Language Processing, Machine Learning, and Deep Learning. The focus of the effort is on understanding the text of business documents. The project includes general NLP and ML techniques plus

analyzing the information content in an initial corpus to identify informational elements
structuring logical forms to represent information appropriately
establishing goals for the system and evaluating how well the system meets those goals
Candidates must have experience with knowledge extraction and knowledge representation that incorporates entities and the relations between them.

Responsibilities include:

Create knowledge extraction system
Develop computational models of language that is readable and appropriate for the domain
Prepare training and testing data
Work with other researchers to understand and integrate with the overall system
Requirements:

Masters degree in computer science or related field
Experience in machine learning, text analysis, and NLP
Experience in algorithm design and modeling
Experience designing and working with ontologies
Programming skills in Java, Python, or similar language