Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Kulkarni, Adithya"'
Autor:
Beigi, Mohammad, Wang, Sijia, Shen, Ying, Lin, Zihao, Kulkarni, Adithya, He, Jianfeng, Chen, Feng, Jin, Ming, Cho, Jin-Hee, Zhou, Dawei, Lu, Chang-Tien, Huang, Lifu
In recent years, Large Language Models (LLMs) have become fundamental to a broad spectrum of artificial intelligence applications. As the use of LLMs expands, precisely estimating the uncertainty in their predictions has become crucial. Current metho
Externí odkaz:
http://arxiv.org/abs/2410.20199
Dependency parsing is an essential task in NLP, and the quality of dependency parsers is crucial for many downstream tasks. Parsers' quality often varies depending on the domain and the language involved. Therefore, it is essential to combat the issu
Externí odkaz:
http://arxiv.org/abs/2403.19183
ChatGPT has recently emerged as a powerful tool for performing diverse NLP tasks. However, ChatGPT has been criticized for generating nonfactual responses, raising concerns about its usability for sensitive tasks like fact verification. This study in
Externí odkaz:
http://arxiv.org/abs/2311.06592
Recent studies have demonstrated that natural-language prompts can help to leverage the knowledge learned by pre-trained language models for the binary sentence-level sentiment classification task. Specifically, these methods utilize few-shot learnin
Externí odkaz:
http://arxiv.org/abs/2305.15689
In this paper, we explore the feasibility of finding algorithm implementations from code. Successfully matching code and algorithms can help understand unknown code, provide reference implementations, and automatically collect data for learning-based
Externí odkaz:
http://arxiv.org/abs/2305.15690
Diverse Natural Language Processing tasks employ constituency parsing to understand the syntactic structure of a sentence according to a phrase structure grammar. Many state-of-the-art constituency parsers are proposed, but they may provide different
Externí odkaz:
http://arxiv.org/abs/2201.07905
Annotation quality and quantity positively affect the learning performance of sequence labeling, a vital task in Natural Language Processing. Hiring domain experts to annotate a corpus is very costly in terms of money and time. Crowdsourcing platform
Externí odkaz:
http://arxiv.org/abs/2109.04470
Autor:
Avudaiappan, Mohanasundaram1 (AUTHOR), Gupta, Himanshu1 (AUTHOR), Gupta, Rajesh1 (AUTHOR), Bhargava, Venu1 (AUTHOR), Kulkarni, Adithya1 (AUTHOR)
Publikováno v:
HPB. 2024 Supplement 3, Vol. 26, pS934-S935. 2p.