Academic Publications

@conference{Gaman2023,

title = {FreCDo: A Large Corpus for French Cross-Domain Dialect Identification},

author = {Mihaela Gaman and Adrian-Gabriel Chifu and William Domingues and Radu-Tudor Ionescu},

editor = {KES International},

url = {https://adrianchifu.com/wp-content/uploads/2023/09/k23-050.pdf},

year  = {2023},

date = {2023-09-05},

urldate = {2023-09-05},

booktitle = {27th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2023)},

publisher = {KES International},

address = {Athens, Greece},

abstract = {We present a novel corpus for French dialect identification comprising 413,522 French text samples collected from public news websites in Belgium, Canada, France and Switzerland. To ensure an accurate estimation of the dialect identification performance of models, we designed the corpus to eliminate potential biases related to topic, writing style, and publication source. More precisely, the training, validation and test splits are collected from different news websites, while searching for different keywords (topics). This leads to a French cross-domain (FreCDo) dialect identification task. We conduct experiments with four competitive baselines, a fine-tuned CamemBERT model, an XGBoost based on fine-tuned CamemBERT features, a Support Vector Machines (SVM) classifier based on fine-tuned CamemBERT features, and an SVM based on word n-grams. Aside from presenting quantitative results, we also make an analysis of the most discriminative features learned by CamemBERT.},

keywords = {Cross-Domain Evaluation, dialect identification, French Corpus},

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}

}