Knowledge-Grounded Dialogue Generation with Term-level De-noising

By Wen Zheng, Natasa Milic-Frayling, Ke Zhou. 2021

15 citations recorded by the source corpus.

Dialogue generation has been improved through injecting knowledge into generative models. However, addition of knowledge through simple selection of sentences or para-graphs is likely to introduce noise and diminish the effectiveness of the generative models. In this paper, we present a novel K nowledge T erm W eighting M odel (KTWM) that incorporates term-level de-noising of the selected knowledge. KTWM includes a module for generating Simulated Response Vectors (SRVs) and uses SRVs attention distributions with the knowledge embeddings to determine knowledge term weights. Our experiments demonstrate that KTWM, combined with various knowledge selection algorithms, consistently achieves statistically significant improvements over methods without term weighting when applied to two publicly available datasets Wizard of Wikipedia (Wiz) and Holl-E. The results are particularly improved for the Wiz test data with unseen topics, demonstrating the robustness of the KTWM noise-reduction approach.

Subfields: Artificial Intelligence