Zobrazeno 1 - 10
of 182
pro vyhledávání: '"Lee, Yeonsoo"'
Autor:
Lee, Seungbeen, Lim, Seungwon, Han, Seungju, Oh, Giyeong, Chae, Hyungjoo, Chung, Jiwan, Kim, Minju, Kwak, Beong-woo, Lee, Yeonsoo, Lee, Dongha, Yeo, Jinyoung, Yu, Youngjae
The idea of personality in descriptive psychology, traditionally defined through observable behavior, has now been extended to Large Language Models (LLMs) to better understand their behavior. This raises a question: do LLMs exhibit distinct and cons
Externí odkaz:
http://arxiv.org/abs/2406.14703
The advent of scalable deep models and large datasets has improved the performance of Neural Machine Translation. Knowledge Distillation (KD) enhances efficiency by transferring knowledge from a teacher model to a more compact student model. However,
Externí odkaz:
http://arxiv.org/abs/2403.01479
Previous work in structured prediction (e.g. NER, information extraction) using single model make use of explicit dataset information, which helps boost in-distribution performance but is orthogonal to robust generalization in real-world situations.
Externí odkaz:
http://arxiv.org/abs/2402.08971
Unsupervised learning objectives like language modeling and de-noising constitute a significant part in producing pre-trained models that perform various downstream applications from natural language understanding to conversational tasks. However, de
Externí odkaz:
http://arxiv.org/abs/2402.08382
Publikováno v:
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (AACL-IJCNLP 2022), pages 895-924
One of the challenges of developing a summarization model arises from the difficulty in measuring the factual inconsistency of the generated text. In this study, we reinterpret the decoder overconfidence-regularizing objective suggested in (Miao et a
Externí odkaz:
http://arxiv.org/abs/2211.12118
Recent neural sequence-to-sequence models with a copy mechanism have achieved remarkable progress in various text generation tasks. These models addressed out-of-vocabulary problems and facilitated the generation of rare words. However, the identific
Externí odkaz:
http://arxiv.org/abs/2112.10360
Autor:
Jang, Yoonna, Lim, Jungwoo, Hur, Yuna, Oh, Dongsuk, Son, Suhyune, Lee, Yeonsoo, Shin, Donghoon, Kim, Seungryong, Lim, Heuiseok
Humans usually have conversations by making use of prior knowledge about a topic and background information of the people whom they are talking to. However, existing conversational agents and datasets do not consider such comprehensive information, a
Externí odkaz:
http://arxiv.org/abs/2112.08619
Autor:
Lee, Yeonsoo Sara, Hayes, Sharonne N., Best, Patricia J.M., Gulati, Rajiv, Gochanour, Benjamin R., Tweet, Marysia S.
Publikováno v:
In CJC Open May 2024 6(5):689-698
Autor:
Seo, Seungmin, Oh, Byungkook, Jeoung, Jeongbeom, Kim, Donghyun, Lee, Kyong-Ho, Shin, Dong-Hoon, Lee, Yeonsoo
Publikováno v:
In Information Sciences October 2023 645
Autor:
Lee, Yeonsoo S., Jenkins, Anna S., Gonzalez-Albo, Giovanni, Ball, Colleen T., Porter, Steven B., Dora, Chandler D.
Publikováno v:
In Urology October 2023 180:209-213