Zobrazeno 1 - 10
of 231
pro vyhledávání: '"Chang Wei Cheng"'
Autor:
Chang, Wei-Cheng, Jiang, Jyun-Yu, Zhang, Jiong, Al-Darabsah, Mutasem, Teo, Choon Hui, Hsieh, Cho-Jui, Yu, Hsiang-Fu, Vishwanathan, S. V. N.
Embedding-based Retrieval Models (ERMs) have emerged as a promising framework for large-scale text retrieval problems due to powerful large language models. Nevertheless, fine-tuning ERMs to reach state-of-the-art results can be expensive due to the
Externí odkaz:
http://arxiv.org/abs/2312.02429
Recent advances in few-shot question answering (QA) mostly rely on the power of pre-trained large language models (LLMs) and fine-tuning in specific settings. Although the pre-training stage has already equipped LLMs with powerful reasoning capabilit
Externí odkaz:
http://arxiv.org/abs/2310.05007
Autor:
Chien, Eli, Zhang, Jiong, Hsieh, Cho-Jui, Jiang, Jyun-Yu, Chang, Wei-Cheng, Milenkovic, Olgica, Yu, Hsiang-Fu
The eXtreme Multi-label Classification~(XMC) problem seeks to find relevant labels from an exceptionally large label space. Most of the existing XMC learners focus on the extraction of semantic features from input query text. However, conventional XM
Externí odkaz:
http://arxiv.org/abs/2305.12349
Uncertainty quantification is one of the most crucial tasks to obtain trustworthy and reliable machine learning models for decision making. However, most research in this domain has only focused on problems with small label spaces and ignored eXtreme
Externí odkaz:
http://arxiv.org/abs/2210.10160
The eXtreme Multi-label text Classification (XMC) problem concerns finding most relevant labels for an input text instance from a large label set. However, the XMC setup faces two challenges: (1) it is not generalizable to predict unseen labels in dy
Externí odkaz:
http://arxiv.org/abs/2112.08652
Autor:
Chien, Eli, Chang, Wei-Cheng, Hsieh, Cho-Jui, Yu, Hsiang-Fu, Zhang, Jiong, Milenkovic, Olgica, Dhillon, Inderjit S
Learning on graphs has attracted significant attention in the learning community due to numerous real-world applications. In particular, graph neural networks (GNNs), which take numerical node features and graph structure as inputs, have been shown t
Externí odkaz:
http://arxiv.org/abs/2111.00064
Extreme multi-label text classification (XMC) seeks to find relevant labels from an extreme large label collection for a given text input. Many real-world applications can be formulated as XMC problems, such as recommendation systems, document taggin
Externí odkaz:
http://arxiv.org/abs/2110.00685
Autor:
Rahman, Abdur, Chang, Wei-Cheng, Kashima, Kaoru, Fukumoto, Yu, Steven Huang, Jyh-Jaan, Löwemark, Ludvig, Wang, Liang-Chi, Chang, Yuan-Pin
Publikováno v:
In Quaternary International 30 May 2024 693:27-37
Partition-based methods are increasingly-used in extreme multi-label classification (XMC) problems due to their scalability to large output spaces (e.g., millions or more). However, existing methods partition the large label space into mutually exclu
Externí odkaz:
http://arxiv.org/abs/2106.12751
Autor:
Chang, Wei-Cheng, Jiang, Daniel, Yu, Hsiang-Fu, Teo, Choon-Hui, Zhang, Jiong, Zhong, Kai, Kolluri, Kedarnath, Hu, Qie, Shandilya, Nikhil, Ievgrafov, Vyacheslav, Singh, Japinder, Dhillon, Inderjit S.
We consider the problem of semantic matching in product search: given a customer query, retrieve all semantically related products from a huge catalog of size 100 million, or more. Because of large catalog spaces and real-time latency constraints, se
Externí odkaz:
http://arxiv.org/abs/2106.12657