Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Oh-Woog Kwon"'
Publikováno v:
ETRI Journal, Vol 46, Iss 1, Pp 137-153 (2024)
This study introduces a new approach in Korean morphological analysis combining dictionary-based techniques with Transformer-based deep learning models. The key innovation is the use of a BERT-based reranking system, significantly enhancing the accur
Externí odkaz:
https://doaj.org/article/cbc3e98b1703412a8679ef5877ec41f1
Publikováno v:
ETRI Journal, Vol 46, Iss 1, Pp 82-95 (2024)
As automated essay scoring (AES) has progressed from handcrafted techniques to deep learning, holistic scoring capabilities have merged. However, specific trait assessment remains a challenge because of the limited depth of earlier methods in modelin
Externí odkaz:
https://doaj.org/article/80b3fe8b3df04735a6fac1bc8e3239c2
Publikováno v:
IEEE Access, Vol 11, Pp 8978-8987 (2023)
A major challenge in education is to provide students with a personalized learning experience. This study aims to address this by developing a dialogue-based intelligent tutoring system (ITS) that imitates human expert tutors. The ITS asks questions,
Externí odkaz:
https://doaj.org/article/f1dd450d5e104f12bff62ed6f652aaa2
Publikováno v:
Applied Sciences, Vol 10, Iss 9, p 3335 (2020)
A conversation is based on internal knowledge that the participants already know or external knowledge that they have gained during the conversation. A chatbot that communicates with humans by using its internal and external knowledge is called a kno
Externí odkaz:
https://doaj.org/article/bf28c8b8ff17498dbcc517ef6bd4320f
Publikováno v:
Applied Sciences, Vol 9, Iss 18, p 3908 (2019)
To generate proper responses to user queries, multi-turn chatbot models should selectively consider dialogue histories. However, previous chatbot models have simply concatenated or averaged vector representations of all previous utterances without co
Externí odkaz:
https://doaj.org/article/6dfa786cad8348cd9e5e0e3b9c367cec
Publikováno v:
Scopus-Elsevier
Document-grounded goal-oriented dialog system understands users’ utterances, and generates proper responses by using information obtained from documents. The Dialdoc21 shared task consists of two subtasks; subtask1, finding text spans associated wi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::71c0a346da588b4fe970a9b3f75e68ba
https://doi.org/10.18653/v1/2021.dialdoc-1.12
https://doi.org/10.18653/v1/2021.dialdoc-1.12
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b38ffca5bdb8c07dfe21c4a3d1a5c412
https://doi.org/10.21437/interspeech.2020-2011
https://doi.org/10.21437/interspeech.2020-2011
Publikováno v:
Applied Sciences
Volume 10
Issue 9
Applied Sciences, Vol 10, Iss 3335, p 3335 (2020)
Volume 10
Issue 9
Applied Sciences, Vol 10, Iss 3335, p 3335 (2020)
A conversation is based on internal knowledge that the participants already know or external knowledge that they have gained during the conversation. A chatbot that communicates with humans by using its internal and external knowledge is called a kno
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ab38c27cca4145c8fb9209bd7bae06fe
Publikováno v:
Computer Speech & Language. 41:146-160
Entropy-based pruning has a limit in selecting a fine distribution of phrase pairs to be pruned in a threshold.Changing the distribution through other divergence metrics improves pruning efficiency in our preliminary empirical analysis.Derived proble
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::af2ccbccdbc8418d70bb84733edd78d0
https://doi.org/10.1016/j.csl.2016.06.006
https://doi.org/10.1016/j.csl.2016.06.006
Publikováno v:
Applied Sciences, Vol 9, Iss 18, p 3908 (2019)
Applied Sciences
Volume 9
Issue 18
Applied Sciences
Volume 9
Issue 18
To generate proper responses to user queries, multi-turn chatbot models should selectively consider dialogue histories. However, previous chatbot models have simply concatenated or averaged vector representations of all previous utterances without co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d73fc3b7ef792718fe2d2afc7cfbf7a9
https://www.mdpi.com/2076-3417/9/18/3908
https://www.mdpi.com/2076-3417/9/18/3908