TSSuBERT: How to Sum Up Multiple Years of Reading in a Few Tweets

Autor: Alexis Dusart, Karen Pinel-Sauvagnat, Gilles Hubert

Publikováno v: ACM Transactions on Information Systems. 41:1-33

The development of deep neural networks and the emergence of pre-trained language models such as BERT allow to increase performance on many NLP tasks. However, these models do not meet the same popularity for tweet stream summarization, which is prob

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9a0ebc9a088da2b32562e90766c178b4
https://doi.org/10.1145/3581786

Does Structure Matter? Leveraging Data-to-Text Generation for Answering Complex Information Needs

Autor: Hanane Djeddal, Thomas Gerald, Laure Soulier, Karen Pinel-Sauvagnat, Lynda Tamine

Publikováno v: Lecture Notes in Computer Science ISBN: 9783030997380

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::2b9c2b3af9be45ec675db2825c48eacc
https://doi.org/10.1007/978-3-030-99739-7_11

ISSumSet: a tweet summarization dataset hidden in a TREC track

Autor: Gilles Hubert, Karen Pinel-Sauvagnat, Alexis Dusart

Publikováno v: SAC '21: Proceedings of the 36th Annual ACM Symposium on Applied Computing ; ISBN: 978-1-4503-8104-8
36th ACM/SIGAPP Symposium on Applied Computing (SAC 2021)
36th ACM/SIGAPP Symposium on Applied Computing (SAC 2021), Association for Computing Machinery-Special Interest Group on Applied Computing (SIGAPP), Mar 2021, Republic of Korea (virtual event), South Korea. pp.665-671, ⟨10.1145/3412841.3441946⟩
SAC

International audience; A key issue for Twitter users relates to the summarization of the continuous and overwhelming stream of information. Many approaches for tweet summarization were proposed in the literature. It is however difficult to compare t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::20138e62c7e79571af422d60da8e97d7
https://hal-univ-tlse3.archives-ouvertes.fr/hal-03244354

Rouletabille at SemEval-2019 Task 4: Neural Network Baseline for Identification of Hyperpartisan Publishers

Autor: Gilles Hubert, Yoann Pitarch, Karen Pinel-Sauvagnat, Jose G. Moreno

Publikováno v: SemEval@NAACL-HLT
HAL
Proceedings of the 13th International Workshop on Semantic Evaluation
13th International Workshop on Semantic Evaluation (SEMEVAL 2019)
13th International Workshop on Semantic Evaluation (SEMEVAL 2019), Jun 2019, Minneapolis, United States. pp.981-984

International audience; This paper describes the Rouletabille participation to the Hyperpartisan News Detection task. We propose the use of different text classification methods for this task. Preliminary experiments using a similar collection used i

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ce93742469fa73e4e30d78641ea24cca
https://oatao.univ-toulouse.fr/24992/

Some thoughts from IRIT about the scenario A of the TREC RTS 2016 and 2017 tracks

Autor: Gilles Hubert, Jose G Moreno, Karen Pinel-Sauvagnat, Yoann Pitarch

Publikováno v: Proceedings TREC 26-NIST Special Publication: SP 500-324
26th Text REtrieval Conference (TREC 2017)
26th Text REtrieval Conference (TREC 2017), Nov 2017, Gaithersburg, Maryland, United States. pp.1-12
HAL

International audience; The TREC Real-Time Summarization (RTS) track provides a framework for evaluating systems monitoring the Twitter stream and pushing tweets to users according to given profiles. It includes metrics, files, settings and hypothesi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::7710f6c2e26b0329efd870421ddc14b2
https://hal.archives-ouvertes.fr/hal-02319737