New paper: Conversation-based multimodal abuse detection through text and graph embeddings
With Noé Cécillon & @r_dufour
Journal: https://t.co/uq45cdL7YM
Preprint: https://t.co/ILnoCPeDEt
New paper: A dataset of the representatives elected in France during the fifth republic
Interdisciplinary work involving political science @NomieFEVRAT and computer science.
Preprint: https://t.co/y62hbtZSRr
Journal: https://t.co/ryYoV1srWG
Introducing ORBITAAL, a large #Bitcoin temporal graph dataset, published in @ScientificData.
ORBITAAL includes link streams & snapshot representations (year, month, day) of user-to-user transactions over 13 years (364M users, 1.6B tr.) https://t.co/7fnu2At5A2
New paper: Approximating Spatial Distance Through Confront Networks: Application to the Segmentation of Medieval Avignon
with Margot Ferrand
Preprint: https://t.co/kmtYAVrQoG
Journal: https://t.co/G8R1I99QYl
Our article (with @VincentLabatut and @r_dufour) titled "The Role of Natural Language Processing Tasks in Automatic Literary Character Network Construction" just got accepted into #COLING2025! Preprint coming soon.
New paper: Interconnected Kingdoms: comparing ‘A Song of Ice and Fire’ adaptations across media using complex networks
with @ArthurAmalvy, M. Janickyj, @Shane_E_M and @PadraigMacC
Journal: https://t.co/EpzBLcO0pI
Preprint: https://t.co/5RJuAH8N59
New paper: Whole-Graph Representation Learning For the Classification of Signed Networks
with Noé Cécillon, @r_dufour and Nejat Arınık
Journal: https://t.co/Bo3urN0Be0…Preprint: https://t.co/s4KPnXw4R9
New paper describing a software to extract character networks from novels, with @ArthurAmalvy and @r_dufour
Just published in the Journal of Open Source Software (JOSS)
https://t.co/goOeldfc29
Allocation de thèse en informatique au LIA (Avignon), équipe Cornet : cf. le lien ci-dessous.
----
Open position for a PhD in Computer Science at LIA, Avignon (France) : see detail below.
----
https://t.co/1QiHC3LlvV
Poste de MCF en section 27 ouvert à Avignon Université, détails au lien ci-dessous.
---
Assistant prof position now available at Avignon University, France. Details below (in French)
-----
https://t.co/CewnYWpy4G
🇨🇳‼️ In China, an engineer came up with anti-mosquito air defense.
-> I’d buy one!
He modified the radar from an electric car to detect insects and attached a powerful laser pointer to it. He collects all the victims in a special “death note.”
An indispensable item for summer.
Our article (@r_dufour@VincentLabatut) "Learning to Rank Context for Named Entity Recognition Using a Synthetic Dataset" just got accepted into #EMNLP2023 main conference! See you there! Preprint coming soon to your nearest arXiv server.
José Saramago only used a comma in the middle of a paragraph and capitalized the first letter of the next sentence to indicate dialogue, lessening authorial presence in the text. What other writers did away with indentations, dashes, quotation marks, colons, etc. to do just this?
Thanks a lot @PiratePeel for the remarkable work as a "recommender". For our latest article with @GiulioRossetti and @dsalvaz, we tested @PCI_networksci. Diamond open access: no cost for authors, no paywall. It was a smooth process, with useful anonymous reviews now open too.
Today: Poster session #ACL2023NLP
16:15-17:45 (Frontenac Ballroom and Queen’s Quay)
📑@ArthurAmalvy@VincentLabatut The Role of Global and Local Context in Named Entity Recognition
🧑🔬@LabrakYanis DrBERT: A Robust Pre-trained Model in French for Biomedical and Clinical domains
After a lot of headaches, I finally released on pypi a (very early) version of Tibert, a coreference resolver compatible with hugginface transformers. It is mainly based on End-to-end Neural Coreference Resolution (Lee et al., 2017). More details at https://t.co/4Yqsyqic1F