Can I read Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference on EtoBox?

Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference by Feng, Yufei; Yang, Xiaoyu; Zhu, Xiaodan; Greenspan, Michael is a scholarly article available to read on EtoBox.

What is Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference about?

We introduce a neuro-symbolic natural logic framework based on reinforcement learning with introspective revision. The model samples and rewards specific reasoning paths through policy gradient, in which the introspective revision algorithm modifies intermediate symbolic reasoning steps to discover reward-earning operations as well as leverages external knowledge to alleviate spurious reasoning and training inefficiency. The framework is supported by properly designed local relation models to avoid input entangling, which helps ensure the interpretability of the proof paths. The proposed model has built-in interpretability and shows superior capability in monotonicity inference, systematic generalization, and interpretability, compared to previous models on the existing datasets.

Author

Feng, Yufei; Yang, Xiaoyu; Zhu, Xiaodan; Greenspan, Michael

Published

2022

Language

EN