Bang LIU – 7 octobre 2021
Titre : Data, Knowledge, and Logic: Modeling and Reasoning for Natural Language Understanding
Résumé:
Existing deep learning-based techniques for different NLU tasks are mostly data-intensive and domain-sensitive. However, creating large-amount and high-quality training datasets for NLU tasks, e.g., question answering, are both expensive and time-consuming. In this talk, we will introduce our research on data generation, knowledge expansion, and reasoning over graphs. Specifically, for data augmentation, we generate large-scale and high-quality question-answer pairs from unlabeled text to augment the training data for question answering. For knowledge expansion, we create and expand an ontology with newly discovered concepts or entities to capture the emerging knowledge in the world and keep the ontology dynamically updated. We will also briefly mention our ongoing work about a reinforcement learning-based relational reasoning framework which reasons over relational data and learns the underlying compositional logical rules. Our long-term vision is to design low-resource, knowledge-empowered, and transferable NLU systems and apply them to different domains
Bio:
Bang Liu is an Assistant Professor in the Department of Computer Science and Operations Research (DIRO) at the University of Montreal, and member of Mila – Quebec Institute of Artificial Intelligence. He researches natural language processing and understanding, text mining, and AI applications in different fields. He has produced visible values to both academia and industry. His innovations have been deployed in real-world applications (QQ Browser, Mobile QQ, and WeChat), serving over a billion daily active users. He has published 25+ papers on top conferences and journals, such as SIGMOD, ACL, NAACL, KDD, WWW, ICDM, CIKM, TKDD, and TON.