AI Seminar Series 2020: Lili Mou on Search-Based Unsupervised Text Generation

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

On April 17, 2020, Dr. Lili Mou — Amii Fellow, Assistant Professor at the University of Alberta, and Canada CIFAR AI Chair — presented Search-Based Unsupervised Text Generation.

His talk features three papers he co-authored which have been accepted at the Annual Conference of the Association for Computational Linguistics (ACL 2020), two of which are currently available here: Unsupervised Paraphrasing by Simulated Annealing and Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction. 

Weaving these papers together, Dr. Mou presents his work on the different applications of search-based unsupervised text generation including paraphrasing, summarization and text simplification. In short: he aims to build text generation agents without training data.

Watch his full presentation below:

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