Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page
Demo Data from SIGIR 2026 / reviewers in the wild / expert

Nicolas Pécheux

dblp:146/3805 · DBLP profile ↗
← Back
3ranked-venue papers
1as first author
0since 2021 · last 2014
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 2 · 1 first-authorGraphics, computer vision, multimedia, augmented reality and games · 1

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
2 papers
Information extraction and text analysis · 100%
Computer graphics and multimedia
1 paper
Audio and music processing · 100%

Topics — the 3 heaviest of 5, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Natural language and speech › Information extraction and text analysis › sequence labeling › part-of-speech tagging
cross-lingual part-of-speech tagging		 0.212014
Cross-Lingual Part-of-Speech Tagging through Ambiguous Learning · EMNLP 2014
Natural language and speech › Information extraction and text analysis › sequence labeling
part-of-speech tagging		 0.212014
Cross-Lingual Part-of-Speech Tagging through Ambiguous Learning · EMNLP 2014
Audio and music processing › speaker recognition
speaker identification		 0.212014
"Sheldon speaking, Bonjour!": Leveraging Multilingual Tracks for (Weakly) Supervised Speaker Identification · ACM Multimedia 2014

Methods — techniques the papers use, named apart from their topics

weakly supervised learning · 0.4automatic alignment · 0.4ambiguous learning · 0.2
YearPublicationVenuePosition
2014 Cross-Lingual Part-of-Speech Tagging through Ambiguous Learning
abstract
International audience
Guillaume Wisniewski, Nicolas Pécheux, Souhir Gahbiche-Braham, François Yvon
 EMNLP2
2014 Rule-based Reordering Space in Statistical Machine Translation
Nicolas Pécheux, Alexandre Allauzen, François Yvon
 LREC1
2014 "Sheldon speaking, Bonjour!": Leveraging Multilingual Tracks for (Weakly) Supervised Speaker Identification
abstract
We address the problem of speaker identification in multimedia data, and TV series in particular. While speaker identification is traditionally a supervised machine-learning task, our first contribution is to significantly reduce the need for costly preliminary manual annotations through the use of automatically aligned (and potentially noisy) fan-generated transcripts and subtitles.
Hervé Bredin, Anindya Roy, Nicolas Pécheux, Alexandre Allauzen
 ACM Multimedia3