Formal knowledge extraction from unstructured text - overview
Knowledge extraction has been an important topic with a wide range of real-world applications. In this project, given unstructured natural language text, we attempt to develop new techniques to construct formal knowledge which can be leveraged by AI domain-independent planning. The end goal of the internship is a research prototype and submissions in top AI conferences (AAAI/IJCAI/ACL/EMNLP/NAACL).
1) Strong programming skills in Python, Java or C++
2) Natural Language Processing and/or Machine Learning research expertise
3) Familiarity with the AI planning/logic (e.g. PDDL) is a plus