Zobrazeno 1 - 10
of 426
pro vyhledávání: '"Li Xianming"'
Publikováno v:
Cailiao gongcheng, Vol 51, Iss 9, Pp 183-191 (2023)
A series of processable and high-temperature resistant polyimide resins terminated with 4-phenylethynyl phthalic anhydride were synthesized by PMR (for in situ polymerization of monomer reactants) using isopropyl alcohol as esterifying agent. The res
Externí odkaz:
https://doaj.org/article/f8b4bae118d0469fb1882825177a5854
BM25, a widely-used lexical search algorithm, remains crucial in information retrieval despite the rise of pre-trained and large language models (PLMs/LLMs). However, it neglects query-document similarity and lacks semantic understanding, limiting it
Externí odkaz:
http://arxiv.org/abs/2408.06643
Publikováno v:
E3S Web of Conferences, Vol 356, p 02030 (2022)
In order to protect the living environment and effectively control the harmful gas composition in the basement of civil air defense in wartime, this paper studies the pollutants of a civil air defense basement project in Jinan by CFD numerical simula
Externí odkaz:
https://doaj.org/article/49304b7a14524672938ab1df0577c66d
High-quality sentence embeddings are fundamental in many natural language processing (NLP) tasks, such as semantic textual similarity (STS) and retrieval-augmented generation (RAG). Nevertheless, most existing methods leverage fixed-length embeddings
Externí odkaz:
http://arxiv.org/abs/2402.14776
Autor:
Li, Xianming, Li, Jing
Social media data exhibits severe redundancy caused by its noisy nature. It leads to increased training time and model bias in its processing. To address this issue, we propose a novel Generative Deduplication framework for social media data selectio
Externí odkaz:
http://arxiv.org/abs/2401.05883
Autor:
Li, Xianming, Li, Jing
Sentence embeddings are crucial in measuring semantic similarity. Most recent studies employed large language models (LLMs) to learn sentence embeddings. Existing LLMs mainly adopted autoregressive architecture without explicit backward dependency mo
Externí odkaz:
http://arxiv.org/abs/2311.05296
Autor:
Li, Zongxi, Li, Xianming, Liu, Yuzhang, Xie, Haoran, Li, Jing, Wang, Fu-lee, Li, Qing, Zhong, Xiaoqin
The recent success of Large Language Models (LLMs) has gained significant attention in both academia and industry. Substantial efforts have been made to enhance the zero- and few-shot generalization capabilities of open-source LLMs through finetuning
Externí odkaz:
http://arxiv.org/abs/2310.01208
Publikováno v:
Gong-kuang zidonghua, Vol 42, Iss 9, Pp 22-26 (2016)
In view of problem that risk assessment for provincial coal mine lacks theory and method, a comprehensive risk assessment method for provincial coal mine accident was proposed: first of all, quantized value of damage extent and occurrence probability
Externí odkaz:
https://doaj.org/article/10f43ee62c3d4a82a04fe21ce0c20272
Autor:
Li, Xianming, Li, Jing
High-quality text embedding is pivotal in improving semantic textual similarity (STS) tasks, which are crucial components in Large Language Model (LLM) applications. However, a common challenge existing text embedding models face is the problem of va
Externí odkaz:
http://arxiv.org/abs/2309.12871
Publikováno v:
Gong-kuang zidonghua, Vol 41, Iss 11, Pp 69-73 (2015)
In view of problems of lack of theoretical system support, poor ability of coordination and difficulty of connecting with different platforms existed in mine emergency command platform in China, combining systems engineering and ICS framework, a hier
Externí odkaz:
https://doaj.org/article/ca7224a1049c496a8cb2188b6e8d3868