Neuro-symbolic Models in Natural Language Inference and Adversarial Attacks: A Case Study with Natural Logic

Xiaodan Zhu (xiaodan (point) zhu <at> queensu (point) ca)

Queen's University

Le 5 avril 2023 à 11 h 30

RĂ©union Zoom, voir http://rali.iro.umontreal.ca/rali/seminaire-virtuel


In this talk I will discuss our recent work on developing neuro-symbolic models for natural language inference. The model combines distributed representation with natural logic to select and modify the intermediate symbolic reasoning steps in order to discover reward-earning operations using reinforcement learning. The model leverages external knowledge to alleviate spurious reasoning paths and increase training efficiency. The proposed method demonstrates a good capability in monotonicity inference, systematic generalization, and interpretability. I will also discuss how to leverage natural logic to develop adversarial attacks to examine if existing models possess the desired property of reasoning.

Recording: https://drive.google.com/file/d/1WBIR0huvPvXPo4423jffGiKAN-_7kGZh/view?usp=share_link


Pour recevoir les annonces hebdomadaires par courriel, visitez http://rali.iro.umontreal.ca/rali/?q=fr/node/1631

Liste des autres séminaires