Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Buru Chang"'
Autor:
Donghyun Son, Byounggyu Lew, Kwanghee Choi, Yongsu Baek, Seungwoo Choi, Beomjun Shin, Sungjoo Ha, Buru Chang
Social media platforms struggle to protect users from harmful content through content moderation. These platforms have recently leveraged machine learning models to cope with the vast amount of user-generated content daily. Since moderation policies
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::98d154a5cf918f37d197abdb2b6c33cf
http://arxiv.org/abs/2208.07522
http://arxiv.org/abs/2208.07522
Autor:
Seungju Han, Beomsu Kim, Jin Yong Yoo, Seokjun Seo, Sangbum Kim, Enkhbayar Erdenee, Buru Chang
In this paper, we consider mimicking fictional characters as a promising direction for building engaging conversation models. To this end, we present a new practical task where only a few utterances of each fictional character are available to genera
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::702781dfe2cfbfc32cac8b18bf440ca7
http://arxiv.org/abs/2204.10825
http://arxiv.org/abs/2204.10825
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198052
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::65b9d87218756915e32e17bb71941dc0
https://doi.org/10.1007/978-3-031-19806-9_41
https://doi.org/10.1007/978-3-031-19806-9_41
Exemplar-based generative models for open-domain conversation produce responses based on the exemplars provided by the retriever, taking advantage of generative models and retrieval models. However, they often ignore the retrieved exemplars while gen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b76a2297a5d428d7ef35c6e80805c5db
http://arxiv.org/abs/2112.06723
http://arxiv.org/abs/2112.06723
Publikováno v:
2021 International Conference on Data Mining Workshops (ICDMW).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0615c7b223f4dddaac7eaaf4a2208620
https://doi.org/10.1109/icdmw53433.2021.00016
https://doi.org/10.1109/icdmw53433.2021.00016
Autor:
Jaewoo Kang, Buru Chang
Publikováno v:
KIISE Transactions on Computing Practices. 25:76-81
약 본 논문은 음식의 재료들을 컴퓨터가 이해할 수 있는 벡터로 표현하는 것을 목표로 한다. 식품공학자들이 재료를 화학 분자의 조합으로 규명해 놓은 데이터에 기반을 두어, 최신 기술인
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::51090c6004fefb035a1f56f401438ddf
https://doi.org/10.5626/ktcp.2019.25.1.76
https://doi.org/10.5626/ktcp.2019.25.1.76
Publikováno v:
CVPR
The current evaluation protocol of long-tailed visual recognition trains the classification model on the long-tailed source label distribution and evaluates its performance on the uniform target label distribution. Such protocol has questionable prac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2f9d637372e5cab9e68eae936a07cfea
https://doi.org/10.1109/cvpr46437.2021.00656
https://doi.org/10.1109/cvpr46437.2021.00656
Publikováno v:
EACL
Several machine learning-based spoiler detection models have been proposed recently to protect users from spoilers on review websites. Although dependency relations between context words are important for detecting spoilers, current attention-based s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::40b1ab7180d3e9ccc39f51cec4988286
Despite the remarkable performance of large-scale generative models in open-domain conversation, they are known to be less practical for building real-time conversation systems due to high latency. On the other hand, retrieval models could return res
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9188e3a2701de33732648b806c6b55d9