@evpure

#NLProc Research scientist @researchdeezer • Also interested in RecSys & IR • Applied in music 🎶 , other creative media 🎧, and digital humanities 📖

 Paris, France
Joined July 2014
  • Tweets53
  • Following87
  • Followers98
1Media
News from our #NLP team! @gaspmichel PhD student in our team present his last work done with @evpure, @romainhennequi1 and @ccerisara at the LaTeCH-CLfL 2024 SIGHUM Workshop in Malta. Preprint available here: arxiv.org/abs/2401.16968 #NLP

Distinguishing Fictional Voices: a Study of Authorship...

Recent approaches to automatically detect the speaker of an utterance of direct speech often disregard general information about characters in favor of local information found in the context, such...

arxiv.org
2
4
495
It seems our account Deezer Research posting mostly about our papers and conference attendance has been suspended here without a clear reason. News will still be posted on our Mastodon instance: sigmoid.social/@researchdeez… and our personal LinkedIn pages.

Deezer Research (@[email protected])

35 Posts, 18 Following, 139 Followers · Researchers and engineers from Deezer. Sharing news about recent studies, papers and conference attendences.

sigmoid.social
1
2
875
Congratulations to Noé Durandard, Gaspard Michel, Viet Anh Tran, and Elena V. Epure (@evpure), for their paper on "Automatic Annotation of Direct Speech in Written French Narratives" accepted at the prestigious #ACL2023 conference! 👏 The paper will be online soon.
3
8
1,032
Fantastic news! 🍾 Elena V. Epure (@evpure) and Romain Hennequin just received an outstanding paper award at the #EACL2023 conference. Congratulations! Paper: aclanthology.org/2023.eacl-m… Code: github.com/deezer/music-ner-…
1
3
17
1,252
This week at #EACL2023, Romain Hennequin will virtually present his research with @evpure (lead author) on named entity recognition in conversational music recommendation queries! Poster: today at 2:15pm (UTC+2) Oral session: tomorrow at 11:15am Paper: aclanthology.org/2023.eacl-m…

A Human Subject Study of Named Entity Recognition in Conversational Music Recommendation Queries

Elena Epure, Romain Hennequin. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. 2023.

aclanthology.org
1
7
966
Our work on Artist and Work of art NER in conversational music recommendation queries comparing humans and models was just accepted at #eacl2023. Our study could be quite relevant for other creative domains too. Code & data to be released soon. cc @romainhennequi1 @researchdeezer
1
1
14
1,425
Three papers involving #Deezer researchers will be presented during the conference, starting today with "Exploiting Device and Audio Data to Tag Music with User-Aware Listening Contexts" by @KarimMajdy @evpure @GeoffroyPeeters and Gaël Richard.
1
1
3
Today at #ISMIR2022: "Network Analyses for Cross-Cultural Music Popularity" by @itskongmeng, @vipulmishra2053, Y. Zhou, @evpure, R. Hennequin, S. Wakamiya, and @ARAMAKI. A great collaboration with #NAIST Japan. Check out the paper, video, and poster: ismir2022program.ismir.net/p…
5
9
In Abu Dhabi attending EMNLP! ☺️ I'll present a full paper done when at @researchdeezer: "Data-Efficient Playlist Captioning With Musical and Linguistic Knowledge" w/ @evpure @romainhennequi1
2
2
18
Elena V. Epure retweeted
Markus Schedl@m_schedl9 Nov 2022
We are #hiring! Vacancy for a full-time 6-year position as university assistant (at postdoc level) in our young research group Multimedia Mining and Search / Human-centered AI at @jku. Details here: jku.at/fileadmin/gruppen/80/… Please share!
4
1
12
Super-happy to have a paper accepted at EMNLP 2022 @emnlpmeeting 🎉 "Data-Efficient Playlist Captioning With Musical and Linguistic Knowledge". Work done with @evpure & Romain Hennequin during my internship at @researchdeezer.
3
2
24
But wait... there'll be even more of @Deezer at #ISMIR2022!🤩 "Network Analyses for Cross-Cultural Music Popularity" by @itskongmeng, @vipulmishra2053, Y. Zhou, @evpure, R. Hennequin, S. Wakamiya, and @ARAMAKI. A great collaboration with #NAIST Japan. Congrats to all authors!
5
16
More great news!🍾 "Exploiting Device and Audio Data to Tag Music with User-Aware Listening Contexts" by @KarimMajdy, @evpure, @GeoffroyPeeters, and Gaël Richard, has also been accepted at #ISMIR2022 @ISMIRConf! A fruitful collaboration between @Deezer and @telecomparis!
2
13
Flow Moods is now used on @Deezer to recommend music by moods to millions of users! 🎵 Congratulations to all co-authors of this #RecSys2022 paper: T. Bontempelli, @xbenji, F. Rigaud, M. Morlon, @MarinLorant, and @gsalhagalvan. More information on: digitalmusicnews.com/2021/10…

Deezer Debuts 'Flow Moods' – Music Matched to Your Mood

Deezer introduces 'Flow Moods' playlists that can track your emotions to play mood-based music. Here's how it works.

digitalmusicnews.com
Guillaume Salha-Galvan
@gsalhagalvan30 Jun 2022
I am thrilled to announce that our "Flow Moods" system, recently deployed in production on @Deezer to recommend music by moods, will be presented as an industry paper at #RecSys2022! 🎉🎉 The paper will be available soon. Stay tuned! @ACMRecSys @researchdeezer @DeezerDevs
1
3
7
Interested in "Explainability in Music Recommender Systems"? Check out our article in @RealAAAI's AI Magazine: onlinelibrary.wiley.com/doi/… A fruitful collaboration between @Deezer and @jkulinz, involving @DAfchar, A. Melchiorre, @m_schedl, R. Hennequin, @evpure, and @MMoussallam!

Explainability in music recommender systems

The most common way to listen to recorded music nowadays is via streaming platforms, which provide access to tens of millions of tracks. To assist users in effectively browsing these large catalogs,...

onlinelibrary.wiley.com
AAAI
@RealAAAI27 Jun 2022
The Summer 2022 issue of #AIMagazine is here. Recommender systems, as used by Netflix, YouTube, and Amazon, are one of the most compelling stories of #AI. Research has led to a continuous improvement of recommendation techniques over the years. Learn more: onlinelibrary.wiley.com/toc/…
1
2
8
New journal paper alert! 🚨 Congratulations to @gsalhagalvan, @JLutzeyer, @GDasoulas, R. Hennequin, and @mvazirg, for their paper on "Modularity-Aware Graph Autoencoders" accepted for publication in @ElsevierConnect's Neural Networks journal (IF: 8.05)! @Deezer @Polytechnique
2
3
4
16
Elena V. Epure @evpure is in Marseille this week! ☀️ She will attend #LREC2022 and present her paper entitled "Probing Pre-trained Auto-regressive Language Models for Named Entity Typing and Recognition" today at 4:30pm. Check it out! arxiv.org/pdf/2108.11857.pdf @lrec2022 @Deezer
2
4
10
Our Director of Research @MMoussallam is attending @VivaTech today in Paris! ☀️ You will find him in this beautiful spot near the entrance and close to food trucks. Reach out if you want to know more about our research work at @DeezerFR! #VivaTech #VivaTech2022
2
9
Last month, @RobinCura presented his recent research entitled "Uplifting Interviews in Social Science with Data Visualization: the case of Music Listening" at the @acm_chi conference! A thread below👇 This work is part of the @BlueBirdRecords project: records.huma-num.fr/
This Post is from an account that no longer exists. Learn more
3
11
Last Tuesday, @DeezerFR hosted the 10th X-IA meetup entitled "State of the Graphs". It included four presentations by graph researchers, including one by @gsalhagalvan from our team on graph-based music recommendation! Find out more about his work: guillaumesalhagalvan.com/doc…
3
1
8
Load more