Academic Publications

@conference{duperis2022,

title = {Deep Unordered Composition for Multi-label Classification applied to Skills Prediction},

author = {Yann Duperis and Adrian-Gabriel Chifu and Bernard Espinasse and Sébastien Fournier and Arthur Kuehn},

url = {http://ceur-ws.org/Vol-3178/CIRCLE_2022_paper_16.pdf},

year  = {2022},

date = {2022-07-04},

urldate = {2022-07-04},

booktitle = {Joint Conference of the Information Retrieval Communities in Europe CIRCLE 2022},

address = {Samatan, France},

abstract = {Today, many recruitment processes are digitalized. Job offers are posted on job boards and candidates apply by submitting their resumes. To select an appropriate candidate for a job, recruiters rely mostly on the evaluation of the professional skills of the individual. However, researches have shown that individuals tend to omit some skills from their professional profile. A human recruiter, knowledgeable in a given activity sector, is often able to fill the gaps and infer the missing skills. In this paper our aim is to support this human recruiter by automatically inferring theses missing skills, a non-trivial task. To solve this task, first we propose a method to tackle the skill prediction problem by transforming it from a multi-label classification task it to a binary classification task. Then we implement this method with a deep learning model inspired by the Deep Unordered Composition approach. Two different variants of this model, one with the Deep Averaging Network architecture and the other with the Set-Transformer architecture, are evaluated on an open IT resumes data set, and the results are promising.},

keywords = {Job recommender system, Natural Language Processing, Neural Networks},

pubstate = {published},

tppubtype = {conference}

}

@conference{ChifuLREC2022,

title = {DeepREF: A Framework for Optimized Deep Learning-based Relation Classification},

author = {Igor Nascimento and Rinaldo Lima and Adrian Chifu and Bernard Espinasse and Sébastien Fournier},

url = {http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.480.pdf},

year  = {2022},

date = {2022-06-20},

urldate = {2022-06-20},

booktitle = {Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022)},

pages = {4513–4522},

publisher = {European Language Resources Association (ELRA)},

address = {Marseille, France},

abstract = {Relation Extraction (RE) is an important basic Natural Language Processing (NLP) task for many applications, including search engines and question-answering systems. There are many studies in this subarea of NLP that continue to be explored, such as the ones concerned by SemEval shared tasks. For many years, several RE systems based on statistical models have been proposed, as well as the frameworks to develop them. We focus on frameworks allowing to develop such RE systems using deep learning models. Such frameworks make it possible to reproduce experiments using many deep learning models and preprocessing techniques. Currently, there are very few frameworks of this type. In this paper, we propose an open and optimizable framework called DeepREF, inspired by two other existing frameworks: OpenNRE and REflex. DeepREF allows the rapid development of deep learning models for Relation Classification (RC). In addition, it enables hyperparameter optimization, and the application of many preprocessing techniques on the input textual data. DeepREF provides means to boost the process of running deep learning models for RC tasks on different datasets and models. DeepREF is evaluated on three reference corpora and has demonstrated competitive results compared to other state-of-the-art RC systems.},

keywords = {DDI, DeepREF, Embeddings, Framework, NLP, Optuna, Relation Classification, SemEval},

pubstate = {published},

tppubtype = {conference}

}

@conference{IonescuChifu2021IJCNN,

title = {FreSaDa: A French Satire Data Set for Cross-Domain Satire Detection},

author = {Radu-Tudor Ionescu and Adrian-Gabriel Chifu},

url = {https://arxiv.org/abs/2104.04828},

year  = {2021},

date = {2021-07-18},

urldate = {2021-07-18},

booktitle = {The International Joint Conference on Neural Network, IJCNN 2021},

series = {IJCNN2021},

abstract = {In this paper, we introduce FreSaDa, a French Satire Data Set, which is composed of 11,570 articles from the news domain. In order to avoid reporting unreasonably high accuracy rates due to the learning of characteristics specific to publication sources, we divided our samples into training, validation and test, such that the training publication sources are distinct from the validation and test publication sources. This gives rise to a cross-domain (cross-source) satire detection task. We employ two classification methods as baselines for our new data set, one based on low-level features (character n-grams) and one based on high-level features (average of CamemBERT word embeddings). As an additional contribution, we present an unsupervised domain adaptation method based on regarding the pairwise similarities (given by the dot product) between the training samples and the validation samples as features. By including these domain-specific features, we attain significant improvements for both character n-grams and CamemBERT embeddings.},

keywords = {Cross-Domain Evaluation, Satire Detection, Text Classification, Unsupervised Domain Adaptation},

pubstate = {published},

tppubtype = {conference}

}

@conference{Duperis2021,

title = {Vers un système de recommandation de profils experts dans l'industrie des procédés},

author = {Yann Duperis and Adrian-Gabriel Chifu and Bernard Espinasse and Sébastien Fournier and Arthur Kuehn},

url = {http://coria.asso-aria.org/2021/articles/long_12/main.pdf},

year  = {2021},

date = {2021-04-15},

urldate = {2021-04-15},

booktitle = {COnférence en Recherche d’Information et Applications},

address = {Grenoble, France (virtuel)},

series = {CORIA2021},

abstract = {La dématérialisation des processus de recrutement n'a pas fait disparaître toutes les frictions inhérentes à cette activité. La recherche automatisée d'un candidat idéal se heurte toujours à la difficulté à modéliser correctement les besoins exprimés en langage naturel dans une offre d’emploi. Le recrutement d’experts, notamment, est particulièrement difficile. En effet, ces profils concernent une proportion réduite des recrutements et leur prise en charge informatisée nécessite une connaissance précise du secteur d’activité concerné. Dans cet article, nous proposons l’architecture d’un système de recommandation de profils experts dans l’industrie des procédés afin d’assister ce type de recrutements.},

keywords = {Expert search, Job recommender system, Semantic web},

pubstate = {published},

tppubtype = {conference}

}

@conference{Chifu2020CIRCLE,

title = {Fair Exposure of Documents in Information Retrieval: a Community Detection Approach},

author = {Adrian Chifu and Josiane Mothe and Md Zia Ullah},

url = {https://www.irit.fr/CIRCLE/wp-content/uploads/2020/06/CIRCLE20_03.pdf},

year  = {2020},

date = {2020-07-01},

booktitle = {Joint Conference of the Information Retrieval Communities in Europe},

series = {CIRCLE2020},

abstract = {While (mainly) designed to answer users’ needs, search engines and recommendation systems do not necessarily guarantee the exposure of the data they store and index while it can be essential for information providers. A recent research direction so called “fair” exposure of documents tackles this problem in information retrieval. It has mainly been cast into a re-ranking problem with constraints and optimization functions. This paper presents the first steps toward a new framework for fair document exposure. This framework is based on document linking and document com- munity detection; communities are used to rank the documents to be retrieved according to an information need. In addition to the first step of this new framework, we present its potential through both a toy example and a few illustrative examples from the 2019 TREC Fair Ranking Track data set.},

keywords = {Document Communities, Document Network, Document Re-ranking, Fair Document Exposure, Information Retrieval, Information Systems},

pubstate = {published},

tppubtype = {conference}

}

@conference{rodrigues2020deepnlpf,

title = {DeepNLPF: A Framework for Integrating Third Party NLP Tools},

author = {Francisco Rodrigues and Rinaldo Lima and William Domingues and Robson Fidalgo and Adrian Chifu and Bernard Espinasse and Sébastien Fournier},

url = {http://www.lrec-conf.org/proceedings/lrec2020/pdf/2020.lrec-1.895.pdf},

year  = {2020},

date = {2020-05-11},

urldate = {2020-01-01},

booktitle = {Proceedings of the 12th Language Resources and Evaluation Conference},

pages = {7244--7251},

series = {LREC2020},

abstract = {Natural Language Processing (NLP) of textual data is usually broken down into a sequence of several subtasks, where the output of one the subtasks becomes the input to the following one, which constitutes an NLP pipeline. Many third-party NLP tools are currently available, each performing distinct NLP subtasks. However, it is difficult to integrate several NLP toolkits into a pipeline due to many problems, including different input/output representations or formats, distinct programming languages, and tokenization issues. This paper presents DeepNLPF, a framework that enables easy integration of third-party NLP tools, allowing the user to preprocess natural language texts at lexical, syntactic, and semantic levels. The proposed framework also provides an API for complete pipeline customization including the definition of input/output formats, integration plugin management, transparent multiprocessing execution strategies, corpus-level statistics, and database persistence. Furthermore, the DeepNLPF user-friendly GUI allows its use even by a non-expert NLP user. We conducted runtime performance analysis showing that DeepNLPF not only easily integrates existent NLP toolkits but also reduces significant runtime processing compared to executing the same NLP pipeline in a sequential manner.},

keywords = {Framework, Natural Language Processing, NLP Tools Integration},

pubstate = {published},

tppubtype = {conference}

}