← Search

Haiying Zhang

2 accepted papers

2022

KGR4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generation

AAAI 2022technical

Generative commonsense reasoning requires machines to generate sentences describing an everyday scenario given several concepts, which has attracted much attention recently. However, existing models cannot perform as well as humans, since sentences they produce are often implausible and grammaticall…

2021

Bridging Subword Gaps in Pretrain-Finetune Paradigm for Natural Language Generation

ACL 2021long

A well-known limitation in pretrain-finetune paradigm lies in its inflexibility caused by the one-size-fits-all vocabulary. This potentially weakens the effect when applying pretrained models into natural language generation (NLG) tasks, especially for the subword distributions between upstream and…