Coronavirus (Covid-19): Latest updates and information
Skip to main content Skip to navigation

Professor Yulan He, Turing AI Acceleration Fellowship

Event-Centric Framework for Natural Language Understanding

Natural Language Understanding (NLU) is a branch of AI that aims to allow computers to understand text automatically. NLU may seem easy to humans, but it's extremely difficult for computers due to the variety, ambiguity, subtlety and expressiveness of human language.

Professor Yulan He's Fellowship focuses on developing a knowledge-aware and event-centric NLU framework that uses evidence, contextual knowledge, common sense and real-world knowledge, allowing computers to understand and infer meaning from text.

Reasoning and inference

For humans, successful reading comprehension depends on the construction of an event structure that represents what is happening in the text, often referred to as the situation model in cognitive psychology. This situation model also involves the integration of prior knowledge with information presented in text for reasoning and inference.

Language understanding requires a combination of relevant evidences, such as from contextual knowledge, common sense or world knowledge, to infer meaning underneath. It also requires a constant update of memory as reading progresses. In machine reading comprehension, a computer could continuously build and update a graph of eventualities as reading progresses. Question-answering could, in principle, be based on such a dynamically updated event graph.

 

In humans, reading comprehension depends on the construction of an event structure that represents what is happening in the text.

The NLU framework will benefit a variety of real-world areas, including drug discovery and healthcare.

During her Fellowship, Professor He will develop a knowledge-aware and event-centric framework for NLU, in which event graphs are built as reading progresses; event representations are learned with the incorporation of background knowledge; implicit knowledge is derived by performing reasoning over event graphs; and the comprehension model is developed with built-in interpretability and robustness against adversarial attacks.

Delivering impact

Since spoken and written communication plays a central part in our daily work and life, the proposed framework will have a profound impact on a variety of application areas, including drug discovery, intelligent virtual assistants, automated customer services, smart home, and question-answering in the finance and legal domains, benefiting industries such as healthcare, finance, law, insurance and education.