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 that requires only weak supervision mined from Wikipedia. We demonstrate the effectiveness and general applicability of our approach on various datasets and diversified model structures.
@article{arxiv.2205.01941,
title = {Lexical Knowledge Internalization for Neural Dialog Generation},
author = {Zhiyong Wu and Wei Bi and Xiang Li and Lingpeng Kong and Ben Kao},
journal= {arXiv preprint arXiv:2205.01941},
year = {2022}
}