most citedLess is More: Rethinking State-of-the-art Continual Relation Extraction Models with a Frustratingly Easy but Effective Approach

5 citations · 11 across the 9 of their papers we have counts for

collaborators

9 papers

cs.CL20235 cited

Making Large Language Models Better Reasoners with Alignment

Peiyi Wang, Lei Li, Liang Chen +5

Reasoning is a cognitive process of using evidence to reach a sound conclusion. The reasoning capability is essential for large language models (LLMs) to serve as the brain of the…

cs.CL2023

Unifying Token and Span Level Supervisions for Few-Shot Sequence Labeling

Zifeng Cheng, Qingyu Zhou, Zhiwei Jiang +3

Few-shot sequence labeling aims to identify novel classes based on only a few labeled samples. Existing methods solve the data scarcity problem mainly by designing token-level or s…

cs.CL2023

Denoising Bottleneck with Mutual Information Maximization for Video Multimodal Fusion

Shaoxiang Wu, Damai Dai, Ziwei Qin +4

Video multimodal fusion aims to integrate multimodal signals in videos, such as visual, audio and text, to make a complementary prediction with multiple modalities contents. Howeve…

cs.CL2023

DialogVCS: Robust Natural Language Understanding in Dialogue System Upgrade

Zefan Cai, Xin Zheng, Tianyu Liu +7

In the constant updates of the product dialogue systems, we need to retrain the natural language understanding (NLU) model as new data from the real users would be merged into the…

cs.CL2023

QURG: Question Rewriting Guided Context-Dependent Text-to-SQL Semantic Parsing

Linzheng Chai, Dongling Xiao, Jian Yang +5

Context-dependent Text-to-SQL aims to translate multi-turn natural language questions into SQL queries. Despite various methods have exploited context-dependence information implic…

cs.CL20231 cited

Enhancing Continual Relation Extraction via Classifier Decomposition

Heming Xia, Peiyi Wang, Tianyu Liu +3

Continual relation extraction (CRE) models aim at handling emerging new relations while avoiding catastrophically forgetting old ones in the streaming data. Though improvements hav…