Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Bout, Andrey"'
The recently proposed ToolkenGPT tool learning paradigm demonstrates promising performance but suffers from two major issues: first, it cannot benefit from tool documentation, and second, it often makes mistakes in whether to use a tool at all. We in
Externí odkaz:
http://arxiv.org/abs/2410.12004
Progress in neural grammatical error correction (GEC) is hindered by the lack of annotated training data. Sufficient amounts of high-quality manually annotated data are not available, so recent research has relied on generating synthetic data, pretra
Externí odkaz:
http://arxiv.org/abs/2311.11813
Autor:
Yakovlev, Konstantin, Podolskiy, Alexander, Bout, Andrey, Nikolenko, Sergey, Piontkovskaya, Irina
Grammatical error correction (GEC) is an important NLP task that is currently usually solved with autoregressive sequence-to-sequence models. However, approaches of this class are inherently slow due to one-by-one token generation, so non-autoregress
Externí odkaz:
http://arxiv.org/abs/2311.08191
Autor:
Yakovlev, Konstantin, Polyakov, Gregory, Alimova, Ilseyar, Podolskiy, Alexander, Bout, Andrey, Nikolenko, Sergey, Piontkovskaya, Irina
A recent trend in multimodal retrieval is related to postprocessing test set results via the dual-softmax loss (DSL). While this approach can bring significant improvements, it usually presumes that an entire matrix of test samples is available as DS
Externí odkaz:
http://arxiv.org/abs/2311.08143
Autor:
Ren, Xiaozhe, Zhou, Pingyi, Meng, Xinfan, Huang, Xinjing, Wang, Yadao, Wang, Weichao, Li, Pengfei, Zhang, Xiaoda, Podolskiy, Alexander, Arshinov, Grigory, Bout, Andrey, Piontkovskaya, Irina, Wei, Jiansheng, Jiang, Xin, Su, Teng, Liu, Qun, Yao, Jun
The scaling of large language models has greatly improved natural language understanding, generation, and reasoning. In this work, we develop a system that trained a trillion-parameter language model on a cluster of Ascend 910 AI processors and MindS
Externí odkaz:
http://arxiv.org/abs/2303.10845
Autor:
Lamanov, Dmitry, Burnyshev, Pavel, Artemova, Ekaterina, Malykh, Valentin, Bout, Andrey, Piontkovskaya, Irina
The recent advances in transfer learning techniques and pre-training of large contextualized encoders foster innovation in real-life applications, including dialog assistants. Practical needs of intent recognition require effective data usage and the
Externí odkaz:
http://arxiv.org/abs/2206.10914
Sub-tasks of intent classification, such as robustness to distribution shift, adaptation to specific user groups and personalization, out-of-domain detection, require extensive and flexible datasets for experiments and evaluation. As collecting such
Externí odkaz:
http://arxiv.org/abs/2108.06991
Real-life applications, heavily relying on machine learning, such as dialog systems, demand out-of-domain detection methods. Intent classification models should be equipped with a mechanism to distinguish seen intents from unseen ones so that the dia
Externí odkaz:
http://arxiv.org/abs/2101.03778
Autor:
Ren, Xiaozhe, Zhou, Pingyi, Meng, Xinfan, Huang, Xinjing, Wang, Yadao, Wang, Weichao, Li, Pengfei, Zhang, Xiaoda, Podolskiy, Alexander, Arshinov, Grigory, Bout, Andrey, Piontkovskaya, Irina, Wei, Jiansheng, Jiang, Xin, Su, Teng, Liu, Qun, Yao, Jun
The scaling of large language models has greatly improved natural language understanding, generation, and reasoning. In this work, we develop a system that trained a trillion-parameter language model on a cluster of Ascend 910 AI processors and MindS
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::76e62a4bbe328d99ea50fb6b38ff8a1c