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 EDBT 2026 / reviewers in the wild / expert

Kevin Löser

dblp:169/3185 · DBLP profile ↗
← Back
3ranked-venue papers
0as first author
0since 2021 · last 2018
—ORCID · none

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

Artificial intelligence and machine learning · 3Graphics, 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
1 paper
Information extraction and text analysis · 87% Representation and self-supervised learning · 13%

Topics — the 2 heaviest of 3, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Natural language and speech › Information extraction and text analysis › morphological analysis
morphological tagging		 0.212015
Non-lexical neural architecture for fine-grained POS Tagging · EMNLP 2015
Natural language and speech › Information extraction and text analysis › sequence labeling
part-of-speech tagging		 0.212015
Non-lexical neural architecture for fine-grained POS Tagging · EMNLP 2015

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

convolutional neural network · 0.2
YearPublicationVenuePosition
2018 Unsupervised Learning of Word Segmentation: Does Tone Matter?
Pierre Godard, Kevin Löser, Alexandre Allauzen, Laurent Besacier, François Yvon
 CICLing (1)2
2016 Preliminary Experiments on Unsupervised Word Discovery in Mboshi
abstract
International audience
Pierre Godard, Gilles Adda, Martine Adda-Decker, Alexandre Allauzen, Laurent Besacier, Hélène Bonneau-Maynard, Guy-Noël Kouarata, Kevin Löser, Annie Rialland, François Yvon
 INTERSPEECH8
2015 Non-lexical neural architecture for fine-grained POS Tagging
abstract
In this paper we explore a POS tagging application of neural architectures that can infer word representations from the raw character stream.It relies on two modelling stages that are jointly learnt: a convolutional network that infers a word representation directly from the character stream, followed by a prediction stage.Models are evaluated on a POS and morphological tagging task for German.Experimental results show that the convolutional network can infer meaningful word representations, while for the prediction stage, a well designed and structured strategy allows the model to outperform stateof-the-art results, without any feature engineering.
Matthieu Labeau, Kevin Löser, Alexandre Allauzen
 EMNLP2