Zobrazeno 1 - 10
of 246
pro vyhledávání: '"Jiang, Daxin"'
Webpage entity extraction is a fundamental natural language processing task in both research and applications. Nowadays, the majority of webpage entity extraction models are trained on structured datasets which strive to retain textual content and it
Externí odkaz:
http://arxiv.org/abs/2403.01698
Previous entity disambiguation (ED) methods adopt a discriminative paradigm, where prediction is made based on matching scores between mention context and candidate entities using length-limited encoders. However, these methods often struggle to capt
Externí odkaz:
http://arxiv.org/abs/2311.03253
Generative approaches powered by large language models (LLMs) have demonstrated emergent abilities in tasks that require complex reasoning abilities. Yet the generative nature still makes the generated content suffer from hallucinations, thus unsuita
Externí odkaz:
http://arxiv.org/abs/2311.03250
Online recommender systems (RS) aim to match user needs with the vast amount of resources available on various platforms. A key challenge is to model user preferences accurately under the condition of data sparsity. To address this challenge, some me
Externí odkaz:
http://arxiv.org/abs/2309.10469
Autor:
Wang, Xindi, Wang, Yufei, Xu, Can, Geng, Xiubo, Zhang, Bowen, Tao, Chongyang, Rudzicz, Frank, Mercer, Robert E., Jiang, Daxin
Large language models (LLMs) have shown remarkable capacity for in-context learning (ICL), where learning a new task from just a few training examples is done without being explicitly pre-trained. However, despite the success of LLMs, there has been
Externí odkaz:
http://arxiv.org/abs/2307.15411
Autor:
Luo, Ziyang, Xu, Can, Zhao, Pu, Sun, Qingfeng, Geng, Xiubo, Hu, Wenxiang, Tao, Chongyang, Ma, Jing, Lin, Qingwei, Jiang, Daxin
Code Large Language Models (Code LLMs), such as StarCoder, have demonstrated exceptional performance in code-related tasks. However, most existing models are solely pre-trained on extensive raw code data without instruction fine-tuning. In this paper
Externí odkaz:
http://arxiv.org/abs/2306.08568
With the advance of large language models (LLMs), the research field of LLM applications becomes more and more popular and the idea of constructing pipelines to accomplish complex tasks by stacking LLM API calls come true. However, this kind of metho
Externí odkaz:
http://arxiv.org/abs/2305.14766
Autor:
Feng, Jiazhan, Tao, Chongyang, Geng, Xiubo, Shen, Tao, Xu, Can, Long, Guodong, Zhao, Dongyan, Jiang, Daxin
Information retrieval (IR) plays a crucial role in locating relevant resources from vast amounts of data, and its applications have evolved from traditional knowledge bases to modern retrieval models (RMs). The emergence of large language models (LLM
Externí odkaz:
http://arxiv.org/abs/2305.07402
Autor:
Chen, Nuo, Shou, Linjun, Gong, Ming, Pei, Jian, Cao, Bowen, Chang, Jianhui, Jiang, Daxin, Li, Jia
Publikováno v:
ACL 2023
Currently, learning better unsupervised sentence representations is the pursuit of many natural language processing communities. Lots of approaches based on pre-trained language models (PLMs) and contrastive learning have achieved promising results o
Externí odkaz:
http://arxiv.org/abs/2305.06154
Autor:
Luo, Ziyang, Xu, Can, Zhao, Pu, Geng, Xiubo, Tao, Chongyang, Ma, Jing, Lin, Qingwei, Jiang, Daxin
Large Language Models (LLMs) have significantly advanced natural language processing (NLP) with their impressive language understanding and generation capabilities. However, their performance may be suboptimal for domain-specific tasks that require s
Externí odkaz:
http://arxiv.org/abs/2305.04757