DSAI Seminar: Neuro-Symbolic Models in NLP (Shalom Lappin)

Many of the neuro-symbolic models used in NLP incorporate tree grammars, or semantic feature markers.These are either directly integrated into the structure of the model, or they are induced as a distributional bias, through distillation learning. The experimental results that these hybrid systems have produced to date tend to be equivocal. They have not yielded strong evidence for the claim that the tree structure component of the model significantly improves its performance on a variety of NLP tasks, if at all. I will consider possible reasons for why this may be the case.

I will also look at different hybrid models applied to tasks in other areas of AI. These may hold out greater promise for significantly improved performance with neuro-symbolic systems.

Password for online participants: monday

About the speaker

Shalom Lappin is Professor of Natural Language Processing at Queen Mary University of London, a Senior Researcher in the Linguistics and Theory of Science unit at the University of Gothenburg, and Professor of Computational Linguistics at King’s College London.