Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Yun, Hyokun"'
Large Language Models (LLMs) have seen widespread adoption due to their remarkable natural language capabilities. However, when deploying them in real-world settings, it is important to align LLMs to generate texts according to acceptable human stand
Externí odkaz:
http://arxiv.org/abs/2407.06443
Autor:
He, Yifei, Zhou, Shiji, Zhang, Guojun, Yun, Hyokun, Xu, Yi, Zeng, Belinda, Chilimbi, Trishul, Zhao, Han
Multi-task learning (MTL) considers learning a joint model for multiple tasks by optimizing a convex combination of all task losses. To solve the optimization problem, existing methods use an adaptive weight updating scheme, where task weights are dy
Externí odkaz:
http://arxiv.org/abs/2402.02009
Finding a high-quality feasible solution to a combinatorial optimization (CO) problem in a limited time is challenging due to its discrete nature. Recently, there has been an increasing number of machine learning (ML) methods for addressing CO proble
Externí odkaz:
http://arxiv.org/abs/2308.00327
Publikováno v:
Proceedings of the 29th International Conference on Computational Linguistics (COLING). 2022
In contrast to traditional exhaustive search, selective search first clusters documents into several groups before all the documents are searched exhaustively by a query, to limit the search executed within one group or only a few groups. Selective s
Externí odkaz:
http://arxiv.org/abs/2209.04378
Reinforcement learning has recently shown promise in learning quality solutions in many combinatorial optimization problems. In particular, the attention-based encoder-decoder models show high effectiveness on various routing problems, including the
Externí odkaz:
http://arxiv.org/abs/2112.12545
Tiering is an essential technique for building large-scale information retrieval systems. While the selection of documents for high priority tiers critically impacts the efficiency of tiering, past work focuses on optimizing it with respect to a stat
Externí odkaz:
http://arxiv.org/abs/2005.07893
Robustness to capitalization errors is a highly desirable characteristic of named entity recognizers, yet we find standard models for the task are surprisingly brittle to such noise. Existing methods to improve robustness to the noise completely disc
Externí odkaz:
http://arxiv.org/abs/1911.05241
Publikováno v:
In Transportation Research Part C March 2023 148
Deep learning has yielded state-of-the-art performance on many natural language processing tasks including named entity recognition (NER). However, this typically requires large amounts of labeled data. In this work, we demonstrate that the amount of
Externí odkaz:
http://arxiv.org/abs/1707.05928
Autor:
Raman, Parameswaran, Srinivasan, Sriram, Matsushima, Shin, Zhang, Xinhua, Yun, Hyokun, Vishwanathan, S. V. N.
Scaling multinomial logistic regression to datasets with very large number of data points and classes is challenging. This is primarily because one needs to compute the log-partition function on every data point. This makes distributing the computati
Externí odkaz:
http://arxiv.org/abs/1604.04706