Zobrazeno 1 - 10
of 40
pro vyhledávání: '"Jacopo Staiano"'
Publikováno v:
EPJ Data Science, Vol 13, Iss 1, Pp 1-41 (2024)
Abstract Over the last decade, several regulatory bodies have started requiring the disclosure of non-financial information from publicly listed companies, in light of the investors’ increasing attention to Environmental, Social, and Governance (ES
Externí odkaz:
https://doaj.org/article/f3f676e3a5004242a0b40384f20c93dc
Autor:
Didem Gundogdu, Ailbhe N. Finnerty, Jacopo Staiano, Stefano Teso, Andrea Passerini, Fabio Pianesi, Bruno Lepri
Publikováno v:
Royal Society Open Science, Vol 4, Iss 9 (2017)
The recent personality psychology literature has coined the name of personality states to refer to states having the same behavioural, affective and cognitive content (described by adjectives) as the corresponding trait, but for a shorter duration. T
Externí odkaz:
https://doaj.org/article/f5bbdf4310254be8be33ef2ceb9afb19
Publikováno v:
IEEE transactions on affective computing, 13(1), 496-507. IEEE
Several lexica for sentiment analysis have been developed and made available in the NLP community. While most of these come with word polarity annotations (e.g. positive/negative), attempts at building lexica for finer-grained emotion analysis (e.g.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9fff542c7ba885fd81851c8c4b11e9fb
https://doi.org/10.1109/taffc.2019.2934444
https://doi.org/10.1109/taffc.2019.2934444
Publikováno v:
2022 International Joint Conference on Neural Networks (IJCNN).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6385c4ef40404949282675aceaf0d0e8
https://doi.org/10.1109/ijcnn55064.2022.9892324
https://doi.org/10.1109/ijcnn55064.2022.9892324
Publikováno v:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Nov 2021, Punta cana, Dominican Republic. ⟨10.18653/v1/2021.emnlp-main.562⟩
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Nov 2021, Punta cana, Dominican Republic. ⟨10.18653/v1/2021.emnlp-main.562⟩
Coupled with the availability of large scale datasets, deep learning architectures have enabled rapid progress on the Question Answering task. However, most of those datasets are in English, and the performances of state-of-the-art multilingual model
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1b8509eb47ab51cd8b28d50f1f887ed1
http://arxiv.org/abs/2010.12643
http://arxiv.org/abs/2010.12643
Publikováno v:
EMNLP (Findings)
In the context of chit-chat dialogues it has been shown that endowing systems with a persona profile is important to produce more coherent and meaningful conversations. Still, the representation of such personas has thus far been limited to a fact-ba
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::89a37b36f39a433c0bfc91c3dff11126
Autor:
Keraron, R., Lancrenon, G., Bras, M., Allary, F., Moyse, G., Scialom, T., Soriano-Morales, E. -P, Jacopo Staiano
Publikováno v:
Scopus-Elsevier
Motivated by the lack of data for non-English languages, in particular for the evaluation of downstream tasks such as Question Answering, we present a participatory effort to collect a native French Question Answering Dataset. Furthermore, we describ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::db197c242138b8a2091d3cb5ed27ebc7
Publikováno v:
HAL
Advances in Neural Information Processing Systems
Advances in Neural Information Processing Systems, Dec 2020, Virtual, Åland Islands. pp.18978-18989
Advances in Neural Information Processing Systems
Advances in Neural Information Processing Systems, Dec 2020, Virtual, Åland Islands. pp.18978-18989
International audience; Training regimes based on Maximum Likelihood Estimation (MLE) suffer from known limitations, often leading to poorly generated text sequences. At the root of these limitations is the mismatch between training and inference, i.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1ca1b4fa8e18a2898ec71791a80c5ea3
Publikováno v:
2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov 2020, Online, France. pp.8051-8067, ⟨10.18653/v1/2020.emnlp-main.647⟩
HAL
EMNLP (1)
2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov 2020, Online, France. pp.8051-8067, ⟨10.18653/v1/2020.emnlp-main.647⟩
HAL
EMNLP (1)
International audience; We present MLSUM, the first large-scale MultiLingual SUMmarization dataset. Obtained from online newspapers, it contains 1.5M+ article/summary pairs in five different languages – namely, French, German, Spanish, Russian, Tur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1dfb2b6a09686f6b8e8fb449ed1a4d82