← Search

Zhichao Geng

2 accepted papers

2022

A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation

ACL 2022findings

Early exiting allows instances to exit at different layers according to the estimation of difficulty. Previous works usually adopt heuristic metrics such as the entropy of internal outputs to measure instance difficulty, which suffers from generalization and threshold-tuning. In contrast, learning t…

2022

Improving Abstractive Dialogue Summarization with Speaker-Aware Supervised Contrastive Learning

COLING 2022main

Pre-trained models have brought remarkable success on the text summarization task. For dialogue summarization, the subdomain of text summarization, utterances are concatenated to flat text before being processed. As a result, existing summarization systems based on pre-trained models are unable to r…

Cited by 12SourcePDFScholar