G
Gaël Dias
Researcher at University of Caen Lower Normandy
Publications - 125
Citations - 1435
Gaël Dias is an academic researcher from University of Caen Lower Normandy. The author has contributed to research in topics: Cluster analysis & Web page. The author has an hindex of 17, co-authored 117 publications receiving 1263 citations. Previous affiliations of Gaël Dias include Universidade Nova de Lisboa & Centre national de la recherche scientifique.
Papers
More filters
Journal ArticleDOI
Survey of Temporal Information Retrieval and Related Applications
TL;DR: A survey of the existing literature on temporal information retrieval is presented, categorize the relevant research, describe the main contributions, and compare different approaches to provide a coherent view of the field.
Journal Article
Using LocalMaxs algorithm for the extraction of contiguous and non-contiguous multiword lexical units
TL;DR: The authors proposed two new association measures, the Symmetric conditional probability (SCP) and the Mutual Expectation (ME), for the extraction of contiguous and non-contiguous MWUs.
Book ChapterDOI
Using LocalMaxs Algorithm for the Extraction of Contiguous and Non-contiguous Multiword Lexical Units
TL;DR: Two new association measures are proposed, the Symmetric Conditional Probability (SCP) and the Mutual Expectation (ME) for the extraction of contiguous and non-contiguous MWUs, used by a new algorithm, the LocalMaxs, that requires neither empirically obtained thresholds nor complex linguistic filters.
Journal ArticleDOI
Multitask Representation Learning for Multimodal Estimation of Depression Level
TL;DR: In this paper, a multitask learning attention-based deep neural network model was proposed to classify the level of depression in the Wizard of Oz interview corpus, where acoustic, textual, and visual modalities were used to train the network.
Proceedings Article
Topic segmentation algorithms for text summarization and passage retrieval: an exhaustive evaluation
TL;DR: A context-based topic segmentation system based on a new informative similarity measure based on word co-occurrence to solve problems of reliability of systems based on lexical repetition and problems of adaptability of language-dependent systems.