Zobrazeno 1 - 10
of 477
pro vyhledávání: '"ZHANG Yunyi"'
Academic paper search is an essential task for efficient literature discovery and scientific advancement. While dense retrieval has advanced various ad-hoc searches, it often struggles to match the underlying academic concepts between queries and doc
Externí odkaz:
http://arxiv.org/abs/2410.19218
Long-context modeling is one of the critical capabilities of language AI for digesting and reasoning over complex information pieces. In practice, long-context capabilities are typically built into a pre-trained language model~(LM) through a carefull
Externí odkaz:
http://arxiv.org/abs/2410.09141
Autor:
Zhang, Yunyi, Zhou, Zhou
Current statistics literature on statistical inference of random fields typically assumes that the fields are stationary or focuses on models of non-stationary Gaussian fields with parametric/semiparametric covariance families, which may not be suffi
Externí odkaz:
http://arxiv.org/abs/2409.01220
Episodic structures are inherently interpretable and adaptable to evolving large-scale key events. However, state-of-the-art automatic event detection methods overlook event episodes and, therefore, struggle with these crucial characteristics. This p
Externí odkaz:
http://arxiv.org/abs/2408.04873
The rapid advancement of Large Language Models (LLMs) highlights the urgent need for evolving evaluation methodologies that keep pace with improvements in language comprehension and information processing. However, traditional benchmarks, which are o
Externí odkaz:
http://arxiv.org/abs/2405.08460
Autor:
Zhang, Yunyi, Yang, Ruozhen, Xu, Xueqiang, Li, Rui, Xiao, Jinfeng, Shen, Jiaming, Han, Jiawei
Hierarchical text classification aims to categorize each document into a set of classes in a label taxonomy. Most earlier works focus on fully or semi-supervised methods that require a large amount of human annotated data which is costly and time-con
Externí odkaz:
http://arxiv.org/abs/2403.00165
Entity set expansion, taxonomy expansion, and seed-guided taxonomy construction are three representative tasks that can be applied to automatically populate an existing taxonomy with emerging concepts. Previous studies view them as three separate tas
Externí odkaz:
http://arxiv.org/abs/2402.13405
Autor:
Zhang, Yu, Zhang, Yunyi, Shen, Yanzhen, Deng, Yu, Popa, Lucian, Shwartz, Larisa, Zhai, ChengXiang, Han, Jiawei
Accurately typing entity mentions from text segments is a fundamental task for various natural language processing applications. Many previous approaches rely on massive human-annotated data to perform entity typing. Nevertheless, collecting such dat
Externí odkaz:
http://arxiv.org/abs/2401.13129
Fine-grained entity typing (FET) is the task of identifying specific entity types at a fine-grained level for entity mentions based on their contextual information. Conventional methods for FET require extensive human annotation, which is time-consum
Externí odkaz:
http://arxiv.org/abs/2310.07795
Autor:
Zhang, Yunyi
Independent or i.i.d. innovations is an essential assumption in the literature for analyzing a vector time series. However, this assumption is either too restrictive for a real-life time series to satisfy or is hard to verify through a hypothesis tes
Externí odkaz:
http://arxiv.org/abs/2310.07364