TSSuBERT: Tweet Stream Summarization Using BERT

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

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 summarization, which can probably b

Externí odkaz: http://arxiv.org/abs/2106.08770

IRIT at TREC 2019: Incident Streams and Complex Answer Retrieval Tracks

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

Publikováno v: The Twenty-Eighth Text REtrieval Conference (TREC 2019) Proceedings
Text REtrieval Conference
Text REtrieval Conference, Nov 2019, Gaithersburg, Maryland USA, Unknown Region

International audience; This paper presents the approaches proposed by the IRIS team of the IRITlaboratory for the TREC Incident Streams and Complex Answer Retrieval tracks. TheIncident Streams (IS) track aims to categorize and prioritize tweets in d

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::f9bf638759acb1f7fee8ffea629e6031
https://hal.science/hal-02976656