AI Seminar Series 2022: Ning Shi

The AI Seminar is a weekly meeting at the University of Alberta where researchers interested in artificial intelligence (AI) can share their research. Presenters include both local speakers from the University of Alberta and visitors from other institutions. Topics can be related in any way to artificial intelligence, from foundational theoretical work to innovative applications of AI techniques to new fields and problems.

On Dec. 23, Ning Shi, a PhD student at the University of Alberta, presented "Cognitively Inspired Natural Language Processing" at the AI Seminar.

Abstract:

Many breakthroughs in one field are inspired by others. For example, neural networks are inspired by the structure and function of the human brain, and attention mechanisms borrow the idea from psychology. Shi presents recent findings in natural language processing inspired by the laws of human cognition, such as knowledge fusion, systematic generalization, and imitation learning. In the first one, he proposes a plug-in framework called RoChBert to build a more robust language model explicitly for Chinese. By incorporating adversarial knowledge, he shows how to fuse the necessary phonetic and glyph information into pre-trained representations to strengthen the robustness. In the next one, we investigate the extent to which neural networks can do the same as humans to generalize from old concepts to new ones systematically. He revisits this controversial topic from the perspective of meaningful learning, a concept from educational psychology. The experimental results indicate that conventional sequence-to-sequence models can successfully one-shot generalize to novel concepts and compositions through shared semantic relationships, either inductively or deductively. In the last one, he reformulates text editing as an imitation game using behavioral cloning. Specifically, he converts standard sequence-to-sequence data into state-to-action demonstrations and propose to train an agent to mimic how humans revise texts iteratively, where the action space can be as flexible as needed. Overall, he hopes this presentation will encourage and shed light on future studies at the junction of multiple fields.

Watch the full presentation below:

Keep up-to-date on the AI Seminar Series by signing up for the mailing list.

Learn how Amii advances world-leading artificial intelligence and machine learning research: visit our Research page.