Mohamed Ben Jannet

Centre National de la Recherche Scientifique

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Olivier Galibert

Laboratoire National de Métrologie et d'Essais

Sophie Rosset

Université Paris-Saclay

Martine Adda‐Decker

Laboratoire de Phonétique et Phonologie

Juliette Kahn

Conservatoire National des Arts et Métiers

Maud Champagne‐Lavau

Centre National de la Recherche Scientifique

Thomas Lavergne

Norwegian Meteorological Institute

Antoine Doucet

La Rochelle Université

Jeremy Leixa

Evaluations and Language resources Distribution Agency

Pierre Zweigenbaum

Université Paris-Saclay

Elvys Linhares Pontes

La Rochelle Université

Cooperative Institutions

Centre National de la Recherche Scientifique

Laboratoire Interdisciplinaire des Sciences du Numérique

Université Paris-Saclay

Institut de Recherche en Informatique de Toulouse

Université Toulouse-I-Capitole

Institut Polytechnique de Bordeaux

Aix-Marseille Université

Laboratoire Parole et Langage

La Rochelle Université

Laboratoire Informatique, Image et Interaction (L3i)

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Using Contextual Sentence Analysis Models to Recognize ESG Concepts

Elvys Linhares Pontes Mohamed Ben Jannet José G. Moreno Antoine Doucet

This paper summarizes the joint participation of the Trading Central Labs and the L3i laboratory of the University of La Rochelle on both sub-tasks of the Shared Task FinSim-4 evaluation campaign. The first sub-task aims to enrich the ‘Fortia ESG taxonomy’ with new lexicon entries while the second one aims to classify sentences to either ‘sustainable’ or ‘unsustainable’ with respect to ESG (Environment, Social and Governance) related factors. For the first sub-task, we proposed a model based on pre-trained Sentence-BERT models to project sentences and concepts in a common space in order to better represent ESG concepts. The official task results show that our system yields a significant performance improvement compared to the baseline and outperforms all other submissions on the first sub-task. For the second sub-task, we combine the RoBERTa model with a feed-forward multi-layer perceptron in order to extract the context of sentences and classify them. Our model achieved high accuracy scores (over 92%) and was ranked among the top 5 systems.

Baseline (sea)

Perceptron

Task Analysis

10.18653/v1/2022.finnlp-1.29

Cite

Citations (10)

Automatic named entity pre-annotation for out-of-domain human annotation

Sophie Rosset Cyril Grouin Thomas Lavergne Mohamed Ben Jannet Jeremy Leixa

Automatic pre-annotation is often used to improve human annotation speed and accuracy. We address here out-of-domain named entity annotation, and examine whether automatic pre-annotation is still beneficial in this setting. Our study design includes two different corpora, three pre-annotation schemes linked to two annotation levels, both expert and novice annotators, a questionnaire-based subjective assessment and a corpus-based quantitative assessment. We observe that preannotation helps in all cases, both for speed and for accuracy, and that the subjective assessment of the annotators does not always match the actual benefits measured in the annotation outcome.

Source

Cite

Citations (8)

ETER: a New Metric for the Evaluation of Hierarchical Named Entity Recognition

HAL (Le Centre pour la Communication Scientifique Directe) (2014)

Mohamed Ben Jannet Martine Adda‐Decker Olivier Galibert Juliette Kahn Sophie Rosset

This paper addresses the question of hierarchical named entity evaluation. In particular, we focus on metrics to deal with complex named entity structures as those introduced within the QUAERO project. The intended goal is to propose a smart way of evaluating partially correctly detected complex entities, beyond the scope of traditional metrics. None of the existing metrics are fully adequate to evaluate the proposed QUAERO task involving entity detection, classification and decomposition. We are discussing the strong and weak points of the existing metrics. We then introduce a new metric, the Entity Tree Error Rate (ETER), to evaluate hierarchical and structured named entity detection, classification and decomposition. The ETER metric builds upon the commonly accepted SER metric, but it takes the complex entity structure into account by measuring errors not only at the slot (or complex entity) level but also at a basic (atomic) entity level. We are comparing our new metric to the standard one using first some examples and then a set of real data selected from the ETAPE evaluation results.

Scope (computer science)

Tree (set theory)

Source

Cite

Citations (46)

How to evaluate ASR output for named entity recognition?

Interspeech 2022 (2015)

Mohamed Ben Jannet Olivier Galibert Martine Adda‐Decker Sophie Rosset

The standard metric to evaluate automatic speech recognition (ASR) systems is the word error rate (WER). WER has proven very useful in stand-alone ASR systems. Nowadays, these systems are often embedded in complex natural language processing systems to perform tasks like speech translation, manmachine dialogue, or information retrieval from speech. This exacerbates the need for the speech processing community to design a new evaluation metric to estimate the quality of automatic transcriptions within their larger applicative context. We introduce a new measure to evaluate ASR in the context of named entity recognition, which makes use of a probabilistic model to estimate the risk of ASR errors inducing downstream errors in named entity detection. Our evaluation, on the ETAPE data, shows that ATENE achieves a higher correlation than WER between the performances in named entities recognition and in automatic speech transcription.

Word error rate

Transcription

Named Entity Recognition

10.21437/interspeech.2015-322

Cite

Citations (18)

How to assess the quality of automatic transcriptions for the extraction of named entities?

Mohamed Ben Jannet Martine Adda‐Decker Olivier Galibert Juliette Kahn Sophie Rosset

Source

Cite

Citations (0)

Prosodic cues of sarcastic speech in French: slower, higher, wider

Interspeech 2022 (2013)

Hélène Lœvenbruck Mohamed Ben Jannet Mariapaola D’Imperio Mathilde Spini Maud Champagne‐Lavau

10.21437/interspeech.2013-761

Cite

Citations (15)