Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Hui, Tingfeng"'
Mixture-of-Experts (MoE) shines brightly in large language models (LLMs) and demonstrates outstanding performance in plentiful natural language processing tasks. However, existing methods transforming LLMs from dense to MoE face significant data requ
Externí odkaz:
http://arxiv.org/abs/2410.01610
Large language models (LLMs) with one or more fine-tuning phases have become a necessary step to unlock various capabilities, enabling LLMs to follow natural language instructions or align with human preferences. However, it carries the risk of catas
Externí odkaz:
http://arxiv.org/abs/2404.18466
Autor:
Zhao, Jinxu, Dong, Guanting, Qiu, Yueyan, Hui, Tingfeng, Song, Xiaoshuai, Guo, Daichi, Xu, Weiran
In a realistic dialogue system, the input information from users is often subject to various types of input perturbations, which affects the slot-filling task. Although rule-based data augmentation methods have achieved satisfactory results, they fai
Externí odkaz:
http://arxiv.org/abs/2402.14494
Autor:
Dong, Guanting, Hui, Tingfeng, GongQue, Zhuoma, Zhao, Jinxu, Guo, Daichi, Zhao, Gang, He, Keqing, Xu, Weiran
Recently, prompt-based generative frameworks have shown impressive capabilities in sequence labeling tasks. However, in practical dialogue scenarios, relying solely on simplistic templates and traditional corpora presents a challenge for these method
Externí odkaz:
http://arxiv.org/abs/2310.10169
Autor:
Dong, Guanting, Zhao, Jinxu, Hui, Tingfeng, Guo, Daichi, Wan, Wenlong, Feng, Boqi, Qiu, Yueyan, Gongque, Zhuoma, He, Keqing, Wang, Zechen, Xu, Weiran
With the increasing capabilities of large language models (LLMs), these high-performance models have achieved state-of-the-art results on a wide range of natural language processing (NLP) tasks. However, the models' performance on commonly-used bench
Externí odkaz:
http://arxiv.org/abs/2310.06504
Autor:
Dong, Guanting, Wang, Zechen, Zhao, Jinxu, Zhao, Gang, Guo, Daichi, Fu, Dayuan, Hui, Tingfeng, Zeng, Chen, He, Keqing, Li, Xuefeng, Wang, Liwen, Cui, Xinyue, Xu, Weiran
The objective of few-shot named entity recognition is to identify named entities with limited labeled instances. Previous works have primarily focused on optimizing the traditional token-wise classification framework, while neglecting the exploration
Externí odkaz:
http://arxiv.org/abs/2308.14533
Autor:
Dong, Guanting, Wang, Zechen, Wang, Liwen, Guo, Daichi, Fu, Dayuan, Wu, Yuxiang, Zeng, Chen, Li, Xuefeng, Hui, Tingfeng, He, Keqing, Cui, Xinyue, Gao, Qixiang, Xu, Weiran
Few-shot named entity recognition (NER) aims at identifying named entities based on only few labeled instances. Most existing prototype-based sequence labeling models tend to memorize entity mentions which would be easily confused by close prototypes
Externí odkaz:
http://arxiv.org/abs/2302.13610
Autor:
Guo, Daichi, Dong, Guanting, Fu, Dayuan, Wu, Yuxiang, Zeng, Chen, Hui, Tingfeng, Wang, Liwen, Li, Xuefeng, Wang, Zechen, He, Keqing, Cui, Xinyue, Xu, Weiran
In real dialogue scenarios, the existing slot filling model, which tends to memorize entity patterns, has a significantly reduced generalization facing Out-of-Vocabulary (OOV) problems. To address this issue, we propose an OOV robust slot filling mod
Externí odkaz:
http://arxiv.org/abs/2302.13584