Academic Publications

@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}

}

@conference{mothe2019predicting,

title = {Predicting Query Difficulty in IR: Impact of Difficulty Definition},

author = {Josiane Mothe and Léa Laporte and Adrian-Gabriel Chifu},

url = {https://www.irit.fr/publis/SIG/2019_KSE_MLC.pdf},

year  = {2019},

date = {2019-10-24},

urldate = {2019-01-01},

booktitle = {2019 11th International Conference on Knowledge and Systems Engineering},

pages = {1--6},

organization = {IEEE},

series = {KSE2019},

abstract = {While it exists information on about any topic on the web, we know from information retrieval (IR) evaluation programs that search systems fail to answer to some queries in an effective manner. System failure is associated to query difficulty in the IR literature. However, there is no clear definition of query difficulty. This paper investigates several ways of defining query difficulty and analyses the impact of these definitions on query difficulty prediction results. Our experiments show that the most stable definition across collections is a threshold-based definition of query difficulty classes.},

keywords = {Information Retrieval, Query Difficulty Prediction, Query Features},

pubstate = {published},

tppubtype = {conference}

}

@conference{chifu2019r2i_lis,

title = {The R2I_LIS Team Proposes Majority Vote for VarDial’s MRC Task},

author = {Adrian-Gabriel Chifu},

url = {https://www.aclweb.org/anthology/W19-1414.pdf},

year  = {2019},

date = {2019-06-01},

urldate = {2019-06-01},

booktitle = {Proceedings of the Sixth Workshop on NLP for Similar Languages, Varieties and Dialects},

pages = {138--143},

series = {VARDIAL2019},

abstract = {This article presents the model that generated the runs submitted by the R2I LIS team to the VarDial2019 evaluation campaign, more particularly, to the binary classification by dialect sub-task of the Moldavian vs. Romanian Cross-dialect Topic identification (MRC) task. The team proposed a majority vote-based model, between five supervised machine learning models, trained on forty manually-crafted features. One of the three submitted runs was ranked second at the binary classification sub-task, with a performance of 0.7963, in terms of macro-F1 measure. The other two runs were ranked third and fourth, respectively.},

keywords = {Competition, Dialect Classification, Feature Engineering, Majority Vote},

pubstate = {published},

tppubtype = {conference}

}

@conference{Espinasse2019,

title = {On the Use of Dependencies in Relation Classification of Text with Deep Learning},

author = {Bernard Espinasse and Sébastien Fournier and Adrian Chifu and Gaël Guibon and René Azcurra and Valentin Mace},

url = {https://hal.archives-ouvertes.fr/hal-02103919/document},

year  = {2019},

date = {2019-04-07},

urldate = {2019-04-07},

booktitle = {20th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing2019)},

series = {CICLing2019},

abstract = {Deep Learning is more and more used in NLP tasks, such as in relation classification of texts. This paper assesses the impact of syntactic dependencies in this task at two levels. The first level concerns the generic Word Embedding (WE) as input of the classification model, the second level concerns the corpus whose relations have to be classified. In this paper, two classification models are studied, the first one is based on a CNN using a generic WE and does not take into account the dependencies of the corpus to be treated, and the second one is based on a compositional WE combining a generic WE with syntactical annotations of this corpus to classify. The impact of dependencies in relation classification is estimated using two different WE. The first one is essentially lexical and trained on the Wikipedia corpus in English, while the second one is also syntactical, trained on the same previously annotated corpus with syntactical dependencies. The two classification models are evaluated on the SemEval 2010 reference corpus using these two generic WE. The experiments show the importance of taking dependencies into account at different levels in the relation classification.},

keywords = {Compositional Word Embedding, Deep Learning, Dependencies, Relation Classification, Word Embedding},

pubstate = {published},

tppubtype = {conference}

}