Lexical Knowledge Internalization for Neural Dialog Generation

Zhiyong Wu, Wei Bi, Xiang Li, Lingpeng Kong, Ben Kao
2022 Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)   unpublished
We propose knowledge internalization (KI), which aims to complement the lexical knowledge into neural dialog models. Instead of further conditioning the knowledge-grounded dialog (KGD) models on externally retrieved knowledge, we seek to integrate knowledge about each input token internally into the model's parameters. To tackle the challenge due to the large scale of lexical knowledge, we adopt the contrastive learning approach and create an effective token-level lexical knowledge retriever
more » ... t requires only weak supervision mined from Wikipedia. We demonstrate the effectiveness and general applicability of our approach on various datasets and diversified model structures.
doi:10.18653/v1/2022.acl-long.547 fatcat:f2tbhusi3bddxjb4nl3g2ppjte