Vincent Labatut
@VincentLabatut
Followers
65
Following
10
Media
11
Statuses
342
MCF en informatique / Assc. Prof. in Computer Science @UnivAvignon @LIAvignon @CERI_Avignon Mastodon: @[email protected]
Avignon
Joined December 2013
New paper: Conversation-based multimodal abuse detection through text and graph embeddings With Noé Cécillon & @r_dufour Journal: https://t.co/uq45cdL7YM Preprint:
hal.science
Abusive behavior is common on online social networks, and forces the hosts of such platforms to find new solutions to address this problem. Various methods have been proposed to automate this task in...
0
1
1
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:
hal.science
The electoral system is a cornerstone of democracy, shaping the structure of political competition, representation, and accountability. In the case of France, it is difficult to access data describ...
0
1
2
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.)
nature.com
Scientific Data - A Temporal Graph Dataset of Bitcoin Entity-Entity Transactions
0
4
1
New paper: Approximating Spatial Distance Through Confront Networks: Application to the Segmentation of Medieval Avignon with Margot Ferrand Preprint: https://t.co/kmtYAVrQoG Journal:
academic.oup.com
Abstract. In historical studies, the older the sources, the more common it is to have access to data that are only partial, and/or unreliable or imprecise.
0
2
1
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.
1
2
4
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:
hal.science
In this article, we propose and apply a method to compare adaptations of the same story across different media. We tackle this task by modelling such adaptations through character networks. We...
0
3
5
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:
hal.science
Graphs are ubiquitous for modeling complex systems involving structured data and relationships. Consequently, graph representation learning, which aims to automatically learn low-dimensional repres...
0
1
1
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
joss.theoj.org
Amalvy et al., (2024). Renard: A Modular Pipeline for Extracting Character Networks from Narrative Texts. Journal of Open Source Software, 9(98), 6574, https://doi.org/10.21105/joss.06574
0
3
6
#RésultatScientifique 🔎 | @ArthurAmalvy, @r_dufour et Vincent Labatut montrent que le découpage de longs textes par des modèles de langue peut nuire à leurs performances et y proposent une solution ➡️ https://t.co/H09ObbKa7c 🤝 @CNRS_dr17 @CentraleNantes @LaboLS2N @LIAvignon
0
5
3
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
0
1
2
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
0
1
1
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.
2
2
16
Justement, on en parlait encore tout à l'heure ! @ArthurAmalvy @r_dufour
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?
1
0
1
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.
My PCI recommendation for Cazabet et al. "Structify-Net: Random Graph generation with controlled size and customized structure" is now online: https://t.co/l2NE4Yo0xV article:
1
3
7
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
2
2
4
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
github.com
End-to-End BERT-Based Coreference System. Contribute to CompNet/Tibert development by creating an account on GitHub.
1
3
3
Postdoc position opening in Lyon, France (2 years), to work with me on network science, dynamic networks, link streams, etc. The exact topic is negotiable, feel free to contact me if you are interested! More Details:
0
16
14
New paper on fraud detection in public procurement, in the framework of the for the DeCoMaP project. Pattern Mining for Anomaly Detection in Graphs: Application to Fraud in Public Procurement -- Preprint: https://t.co/Sp89uCvKtV -- DeCoMaP project:
anr.fr
The opening up of public data (on public procurement and court decisions) now offers in France the opportunity to combine data from contracts between public buyers and selected companies with data on...
0
0
2