no code implementations • EMNLP 2021 • Kunihiro Takeoka, Kosuke Akimoto, Masafumi Oyamada
Conventional supervised methods for this enrichment task fail to find optimal parents of new terms in low-resource settings where only small taxonomies are available because of overfitting to hierarchical relationships in the taxonomies.
no code implementations • 21 Mar 2024 • Kosuke Akimoto, Kunihiro Takeoka, Masafumi Oyamada
Finally, based on these observations, we propose a method to mitigate overfitting to specific context quality by introducing bias to the cross-attention distribution, which we demonstrate to be effective in improving the performance of FiD models on different context quality.
no code implementations • 4 Dec 2023 • Haochen Zhang, Yuyang Dong, Chuan Xiao, Masafumi Oyamada
This paper explores the utilization of LLMs for data preprocessing (DP), a crucial step in the data mining pipeline that transforms raw data into a clean format conducive to easy processing.
no code implementations • 30 Aug 2023 • Haochen Zhang, Yuyang Dong, Chuan Xiao, Masafumi Oyamada
Large Language Models (LLMs), typified by OpenAI's GPT series and Meta's LLaMA variants, have marked a significant advancement in artificial intelligence.
no code implementations • 15 Dec 2022 • Yuyang Dong, Chuan Xiao, Takuma Nozawa, Masafumi Enomoto, Masafumi Oyamada
They are either exact solutions whose running time is linear in the sizes of query column and target table repository or approximate solutions lacking precision.
no code implementations • 18 Apr 2022 • Yuyang Dong, Masafumi Oyamada
Data scientists are constantly facing the problem of how to improve prediction accuracy with insufficient tabular data.
no code implementations • 26 Oct 2020 • Yuyang Dong, Kunihiro Takeoka, Chuan Xiao, Masafumi Oyamada
Finding joinable tables in data lakes is key procedure in many applications such as data integration, data augmentation, data analysis, and data market.