Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Gan, Yujian"'
We introduce ClarQ-LLM, an evaluation framework consisting of bilingual English-Chinese conversation tasks, conversational agents and evaluation metrics, designed to serve as a strong benchmark for assessing agents' ability to ask clarification quest
Externí odkaz:
http://arxiv.org/abs/2409.06097
In text-to-SQL tasks -- as in much of NLP -- compositional generalization is a major challenge: neural networks struggle with compositional generalization where training and test distributions differ. However, most recent attempts to improve this are
Externí odkaz:
http://arxiv.org/abs/2205.02054
Recently, there has been significant progress in studying neural networks for translating text descriptions into SQL queries under the zero-shot cross-domain setting. Despite achieving good performance on some public benchmarks, we observe that exist
Externí odkaz:
http://arxiv.org/abs/2109.05157
Autor:
Gan, Yujian, Chen, Xinyun, Xie, Jinxia, Purver, Matthew, Woodward, John R., Drake, John, Zhang, Qiaofu
Addressing the mismatch between natural language descriptions and the corresponding SQL queries is a key challenge for text-to-SQL translation. To bridge this gap, we propose an SQL intermediate representation (IR) called Natural SQL (NatSQL). Specif
Externí odkaz:
http://arxiv.org/abs/2109.05153
Autor:
Gan, Yujian, Chen, Xinyun, Huang, Qiuping, Purver, Matthew, Woodward, John R., Xie, Jinxia, Huang, Pengsheng
Recently, there has been significant progress in studying neural networks to translate text descriptions into SQL queries. Despite achieving good performance on some public benchmarks, existing text-to-SQL models typically rely on the lexical matchin
Externí odkaz:
http://arxiv.org/abs/2106.01065
Autor:
Fan Yajing, Gan Yujian
Publikováno v:
ICBK
Recently pattern recognition in stock trading is more and more important as studies showed that stock patterns could implicate useful information for stock price trading. Correct patterns recognition would help traders detect trading time. This study
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e6f66c02ce94fae1a4365bfd0badee00
https://doi.org/10.1109/icbk.2017.51
https://doi.org/10.1109/icbk.2017.51
