Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Ce travail a pour objectif de montrer l'intérêt d'une évaluation linguistique des résultats d'analyses syntaxiques effectuées par les modèles statistiques développés pour le Traitement Automatique des Langues (TAL), dans ce cas le modèle fr-dep-news-trf de spaCy. Nous montrons également l'intérêt de réaliser cette évaluation sur un corpus littéraire contenant de nombreuses difficultés syntaxiques, le recueil Flaques de verre de Pierre Reverdy. Dans un premier temps, nous réalisons une évaluation automatique des résultats pour situer les performances du modèle par rapport aux données déjà disponibles à son sujet. Nous analysons ensuite les erreurs individuellement selon divers paramètres linguistiques, notamment la cohérence, la longueur des dépendances et le flux de dépendance, puis dressons une typologie des erreurs selon des structures et fonctions syntaxiques. Nous montrons que l'analyse est perturbée par des particularités syntaxiques de notre corpus littéraire, mais également qu'elle semble être limitée par les règles d'annotation sélectionnées pour l'entrainement du modèle, Universal Dependencies. Enfin, nous terminons l'exposé par une discussion concernant l'intérêt du TAL pour les études littéraires, en particulier la stylistique.

Traitement Automatique des Langues --- Parsing syntaxique --- Évaluation linguistique --- spaCy --- Universal Dependencies --- Pierre Reverdy --- Grammaire dépendancielle --- Arts & sciences humaines > Langues & linguistique

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Current approaches to Natural Language Processing (NLP) have shown impressive improvements in many important tasks: machine translation, language modeling, text generation, sentiment/emotion analysis, natural language understanding, and question answering, among others. The advent of new methods and techniques, such as graph-based approaches, reinforcement learning, or deep learning, have boosted many NLP tasks to a human-level performance (and even beyond). This has attracted the interest of many companies, so new products and solutions can benefit from advances in this relevant area within the artificial intelligence domain.This Special Issue reprint, focusing on emerging techniques and trendy applications of NLP methods, reports on some of these achievements, establishing a useful reference for industry and researchers on cutting-edge human language technologies.

Technology: general issues --- History of engineering & technology --- natural language processing --- distributional semantics --- machine learning --- language model --- word embeddings --- machine translation --- sentiment analysis --- quality estimation --- neural machine translation --- pretrained language model --- multilingual pre-trained language model --- WMT --- neural networks --- recurrent neural networks --- named entity recognition --- multi-modal dataset --- Wikimedia Commons --- multi-modal language model --- concreteness --- curriculum learning --- electronic health records --- clinical text --- relationship extraction --- text classification --- linguistic corpus --- deception --- linguistic cues --- statistical analysis --- discriminant function analysis --- fake news detection --- stance detection --- social media --- abstractive summarization --- monolingual models --- multilingual models --- transformer models --- transfer learning --- discourse analysis --- problem-solution pattern --- automatic classification --- machine learning classifiers --- deep neural networks --- question answering --- machine reading comprehension --- query expansion --- information retrieval --- multinomial naive bayes --- relevance feedback --- cause-effect relation --- transitive closure --- word co-occurrence --- automatic hate speech detection --- multisource feature extraction --- Latin American Spanish language models --- fine-grained named entity recognition --- k-stacked feature fusion --- dual-stacked output --- unbalanced data problem --- document representation --- semantic analysis --- conceptual modeling --- universal representation --- trend analysis --- topic modeling --- Bert --- geospatial data technology and application --- attention model --- dual multi-head attention --- inter-information relationship --- question difficult estimation --- named-entity recognition --- BERT model --- conditional random field --- pre-trained model --- fine-tuning --- feature fusion --- attention mechanism --- task-oriented dialogue systems --- Arabic --- multi-lingual transformer model --- mT5 --- language marker --- mental disorder --- deep learning --- LIWC --- spaCy --- RobBERT --- fastText --- LIME --- conversational AI --- intent detection --- slot filling --- retrieval-based question answering --- query generation --- entity linking --- knowledge graph --- entity embedding --- global model --- DISC model --- personality recognition --- predictive model --- text analysis --- data privacy --- federated learning --- transformer --- natural language processing --- distributional semantics --- machine learning --- language model --- word embeddings --- machine translation --- sentiment analysis --- quality estimation --- neural machine translation --- pretrained language model --- multilingual pre-trained language model --- WMT --- neural networks --- recurrent neural networks --- named entity recognition --- multi-modal dataset --- Wikimedia Commons --- multi-modal language model --- concreteness --- curriculum learning --- electronic health records --- clinical text --- relationship extraction --- text classification --- linguistic corpus --- deception --- linguistic cues --- statistical analysis --- discriminant function analysis --- fake news detection --- stance detection --- social media --- abstractive summarization --- monolingual models --- multilingual models --- transformer models --- transfer learning --- discourse analysis --- problem-solution pattern --- automatic classification --- machine learning classifiers --- deep neural networks --- question answering --- machine reading comprehension --- query expansion --- information retrieval --- multinomial naive bayes --- relevance feedback --- cause-effect relation --- transitive closure --- word co-occurrence --- automatic hate speech detection --- multisource feature extraction --- Latin American Spanish language models --- fine-grained named entity recognition --- k-stacked feature fusion --- dual-stacked output --- unbalanced data problem --- document representation --- semantic analysis --- conceptual modeling --- universal representation --- trend analysis --- topic modeling --- Bert --- geospatial data technology and application --- attention model --- dual multi-head attention --- inter-information relationship --- question difficult estimation --- named-entity recognition --- BERT model --- conditional random field --- pre-trained model --- fine-tuning --- feature fusion --- attention mechanism --- task-oriented dialogue systems --- Arabic --- multi-lingual transformer model --- mT5 --- language marker --- mental disorder --- deep learning --- LIWC --- spaCy --- RobBERT --- fastText --- LIME --- conversational AI --- intent detection --- slot filling --- retrieval-based question answering --- query generation --- entity linking --- knowledge graph --- entity embedding --- global model --- DISC model --- personality recognition --- predictive model --- text analysis --- data privacy --- federated learning --- transformer