Shengyu Mao


2023

pdf
Knowledge Rumination for Pre-trained Language Models
Yunzhi Yao | Peng Wang | Shengyu Mao | Chuanqi Tan | Fei Huang | Huajun Chen | Ningyu Zhang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Previous studies have revealed that vanilla pre-trained language models (PLMs) lack the capacity to handle knowledge-intensive NLP tasks alone; thus, several works have attempted to integrate external knowledge into PLMs. However, despite the promising outcome, we empirically observe that PLMs may have already encoded rich knowledge in their pre-trained parameters but fails to fully utilize them when applying to knowledge-intensive tasks. In this paper, we propose a new paradigm dubbed Knowledge Rumination to help the pre-trained language model utilize that related latent knowledge without retrieving them from the external corpus. By simply adding a prompt like “As far as I know” to the PLMs, we try to review related latent knowledge and inject them back into the model for knowledge consolidation. We apply the proposed knowledge rumination to various language models, including RoBERTa, DeBERTa, and GPT-3. Experimental results on six commonsense reasoning tasks and GLUE benchmarks demonstrate the effectiveness of our proposed approach, which proves that the knowledge stored in PLMs can be better exploited to enhance performance.

pdf
SPEECH: Structured Prediction with Energy-Based Event-Centric Hyperspheres
Shumin Deng | Shengyu Mao | Ningyu Zhang | Bryan Hooi
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Event-centric structured prediction involves predicting structured outputs of events. In most NLP cases, event structures are complex with manifold dependency, and it is challenging to effectively represent these complicated structured events. To address these issues, we propose Structured Prediction with Energy-based Event-Centric Hyperspheres (SPEECH). SPEECH models complex dependency among event structured components with energy-based modeling, and represents event classes with simple but effective hyperspheres. Experiments on two unified-annotated event datasets indicate that SPEECH is predominant in event detection and event-relation extraction tasks.