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{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}

}