Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Samuel Louvan"'
Autor:
Bernardo Magnini, Samuel Louvan
Publikováno v:
Handbook of Cognitive Mathematics ISBN: 9783030449827
Handbook of Cognitive Mathematics ISBN: 9783031039447
Handbook of Cognitive Mathematics ISBN: 9783031039447
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1260e9fb2a20ecacc8ce501758a3ca7b
https://doi.org/10.1007/978-3-030-44982-7_20-1
https://doi.org/10.1007/978-3-030-44982-7_20-1
Autor:
Samuel Louvan, Bernardo Magnini
Publikováno v:
COLING
In recent years, fostered by deep learning technologies and by the high demand for conversational AI, various approaches have been proposed that address the capacity to elicit and understand user's needs in task-oriented dialogue systems. We focus on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eb15e0d6a320cc0f88426862612a9cdf
http://arxiv.org/abs/2011.00564
http://arxiv.org/abs/2011.00564
Autor:
Bernardo Magnini, Samuel Louvan
Publikováno v:
Insights
Although several works have addressed the role of data selection to improve transfer learning for various NLP tasks, there is no consensus about its real benefits and, more generally, there is a lack of shared practices on how it can be best applied.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3b4bbd12753e77b0dfbaa9247ad4c276
https://doi.org/10.18653/v1/2020.insights-1.3
https://doi.org/10.18653/v1/2020.insights-1.3
Autor:
Bernardo Magnini, Samuel Louvan
Publikováno v:
SIGdial
Slot filling is a core operation for utterance understanding in task-oriented dialogue systems. Slots are typically domain-specific, and adding new domains to a dialogue system involves data and time-intensive processes. A popular technique to addres
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5bce3b4f31f7aac659766c2ad4e760ea
https://doi.org/10.18653/v1/w19-5911
https://doi.org/10.18653/v1/w19-5911
Autor:
Samuel Louvan, Kemal Kurniawan
Publikováno v:
IALP
Automatic text summarization is generally considered as a challenging task in the NLP community. One of the challenges is the publicly available and large dataset that is relatively rare and difficult to construct. The problem is even worse for low-r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eeefa836bf51322d14ac40c7c32920f5
http://arxiv.org/abs/1810.05334
http://arxiv.org/abs/1810.05334
Autor:
Samuel Louvan, Kemal Kurniawan
Publikováno v:
NUT@EMNLP
Despite the long history of named-entity recognition (NER) task in the natural language processing community, previous work rarely studied the task on conversational texts. Such texts are challenging because they contain a lot of word variations whic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f26e7d756676b4ac2e5da1e0ac4d3997
http://arxiv.org/abs/1805.12291
http://arxiv.org/abs/1805.12291
Publikováno v:
2018 4th International Conference on Computer and Technology Applications (ICCTA).
The Internet has many benefits, some of them are to gain knowledge and gain the latest information. The internet can be used by anyone and can contain any information, including negative content such as pornographic content, radicalism, racial intole
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::21353a32ec01871229388fc12e8fa5b9
https://doi.org/10.1109/cata.2018.8398674
https://doi.org/10.1109/cata.2018.8398674
Autor:
Samuel Louvan, Alfan Farizki Wicaksono, Kemal Kurniawan, Fariz Ikhwantri, Valdi Rachman, Bagas Abisena, Rahmad Mahendra
Publikováno v:
DeepLo@ACL
Most Semantic Role Labeling (SRL) approaches are supervised methods which require a significant amount of annotated corpus, and the annotation requires linguistic expertise. In this paper, we propose a Multi-Task Active Learning framework for Semanti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cc96fad948d97ced2665c85475f99a86
https://doi.org/10.18653/v1/w18-3406
https://doi.org/10.18653/v1/w18-3406