1,720,969 research outputs found
Evaluation et amélioration des capacités de raisonnement des Modèles de Langage
No full textThis thesis focuses on evaluating and improving the reasoning abilities of Smaller Language Models (SLMs) and Large Language Models (LLMs). It explores SLMs’ performance on complex tasks and their limitations with simpler ones. This thesis introduces LogiTorch, a Python library that facilitates the training of models on various reasoning tasks with minimal coding.It also presents TINA, a negated data augmentation technique that improves SLMs’ robustness to Negation in textual entailment tasks. Further, this thesis explores LLMs’ capabilities through MAFALDA, a new benchmark for identifying and classifying reasoning fallacies, proposing a new annotation scheme and evaluation metric that considers subjectivity in reasoning. The findings indicate that humans outperform SLMs and LLMs in this reasoning task. We propose several research directions that merit further investigation, such as investigating Neuro-symbolic AI and improving the reasoning abilities of low-resource LLMs.Cette thèse examine les capacités de raisonnement des Petits Modèles de Langage (SLMs) et Grands Modèles de Langage (LLMs) et expose leurs limites. Elle présente LogiTorch, une bibliothèque Python facilitant l’entraînement de modèles sur diverses tâches de raisonnement. La thèse inclut également TINA, une technique d’augmentation de données qui renforce la robustesse des SLMs face à la négation dans les tâches d’implication textuelle. De plus, la thèse explore les capacités des LLMs avec MAFALDA, un nouveau benchmark pour la classification des sophismes, intégrant une métrique d’évaluation quiconsidère la subjectivité. Les résultats montrent que les humains surpassent les modèles dans cette tâche de raisonnement. Nous proposons plusieurs directions de recherche qui méritent une investigation plus approfondie, telles que l’exploration de l’IA Neurosymbolique et l’amélioration des capacités de raisonnement des LLMs à faibles ressources
Evaluation et amélioration des capacités de raisonnement des Modèles de Langage
No full textThis thesis focuses on evaluating and improving the reasoning abilities of Smaller Language Models (SLMs) and Large Language Models (LLMs). It explores SLMs’ performance on complex tasks and their limitations with simpler ones. This thesis introduces LogiTorch, a Python library that facilitates the training of models on various reasoning tasks with minimal coding.It also presents TINA, a negated data augmentation technique that improves SLMs’ robustness to Negation in textual entailment tasks. Further, this thesis explores LLMs’ capabilities through MAFALDA, a new benchmark for identifying and classifying reasoning fallacies, proposing a new annotation scheme and evaluation metric that considers subjectivity in reasoning. The findings indicate that humans outperform SLMs and LLMs in this reasoning task. We propose several research directions that merit further investigation, such as investigating Neuro-symbolic AI and improving the reasoning abilities of low-resource LLMs.Cette thèse examine les capacités de raisonnement des Petits Modèles de Langage (SLMs) et Grands Modèles de Langage (LLMs) et expose leurs limites. Elle présente LogiTorch, une bibliothèque Python facilitant l’entraînement de modèles sur diverses tâches de raisonnement. La thèse inclut également TINA, une technique d’augmentation de données qui renforce la robustesse des SLMs face à la négation dans les tâches d’implication textuelle. De plus, la thèse explore les capacités des LLMs avec MAFALDA, un nouveau benchmark pour la classification des sophismes, intégrant une métrique d’évaluation quiconsidère la subjectivité. Les résultats montrent que les humains surpassent les modèles dans cette tâche de raisonnement. Nous proposons plusieurs directions de recherche qui méritent une investigation plus approfondie, telles que l’exploration de l’IA Neurosymbolique et l’amélioration des capacités de raisonnement des LLMs à faibles ressources
Evaluation et amélioration des capacités de raisonnement des Modèles de Langage
No full textThis thesis focuses on evaluating and improving the reasoning abilities of Smaller Language Models (SLMs) and Large Language Models (LLMs). It explores SLMs’ performance on complex tasks and their limitations with simpler ones. This thesis introduces LogiTorch, a Python library that facilitates the training of models on various reasoning tasks with minimal coding.It also presents TINA, a negated data augmentation technique that improves SLMs’ robustness to Negation in textual entailment tasks. Further, this thesis explores LLMs’ capabilities through MAFALDA, a new benchmark for identifying and classifying reasoning fallacies, proposing a new annotation scheme and evaluation metric that considers subjectivity in reasoning. The findings indicate that humans outperform SLMs and LLMs in this reasoning task. We propose several research directions that merit further investigation, such as investigating Neuro-symbolic AI and improving the reasoning abilities of low-resource LLMs.Cette thèse examine les capacités de raisonnement des Petits Modèles de Langage (SLMs) et Grands Modèles de Langage (LLMs) et expose leurs limites. Elle présente LogiTorch, une bibliothèque Python facilitant l’entraînement de modèles sur diverses tâches de raisonnement. La thèse inclut également TINA, une technique d’augmentation de données qui renforce la robustesse des SLMs face à la négation dans les tâches d’implication textuelle. De plus, la thèse explore les capacités des LLMs avec MAFALDA, un nouveau benchmark pour la classification des sophismes, intégrant une métrique d’évaluation quiconsidère la subjectivité. Les résultats montrent que les humains surpassent les modèles dans cette tâche de raisonnement. Nous proposons plusieurs directions de recherche qui méritent une investigation plus approfondie, telles que l’exploration de l’IA Neurosymbolique et l’amélioration des capacités de raisonnement des LLMs à faibles ressources
Evaluation et amélioration des capacités de raisonnement des Modèles de Langage
No full textCette thèse examine les capacités de raisonnement des Petits Modèles de Langage (SLMs) et Grands Modèles de Langage (LLMs) et expose leurs limites. Elle présente LogiTorch, une bibliothèque Python facilitant l’entraînement de modèles sur diverses tâches de raisonnement. La thèse inclut également TINA, une technique d’augmentation de données qui renforce la robustesse des SLMs face à la négation dans les tâches d’implication textuelle. De plus, la thèse explore les capacités des LLMs avec MAFALDA, un nouveau benchmark pour la classification des sophismes, intégrant une métrique d’évaluation quiconsidère la subjectivité. Les résultats montrent que les humains surpassent les modèles dans cette tâche de raisonnement. Nous proposons plusieurs directions de recherche qui méritent une investigation plus approfondie, telles que l’exploration de l’IA Neurosymbolique et l’amélioration des capacités de raisonnement des LLMs à faibles ressources.This thesis focuses on evaluating and improving the reasoning abilities of Smaller Language Models (SLMs) and Large Language Models (LLMs). It explores SLMs’ performance on complex tasks and their limitations with simpler ones. This thesis introduces LogiTorch, a Python library that facilitates the training of models on various reasoning tasks with minimal coding.It also presents TINA, a negated data augmentation technique that improves SLMs’ robustness to Negation in textual entailment tasks. Further, this thesis explores LLMs’ capabilities through MAFALDA, a new benchmark for identifying and classifying reasoning fallacies, proposing a new annotation scheme and evaluation metric that considers subjectivity in reasoning. The findings indicate that humans outperform SLMs and LLMs in this reasoning task. We propose several research directions that merit further investigation, such as investigating Neuro-symbolic AI and improving the reasoning abilities of low-resource LLMs
Arabic named entity recognition via deep co-learning
Full text linkNamed entity recognition (NER) is an important natural language processing (NLP) task with many applications. We tackle the problem of Arabic NER using deep learning based on Arabic word embeddings that capture syntactic and semantic relationships between words. Deep learning has been shown to perform significantly better than other approaches for various NLP tasks including NER. However, deep-learning models also require a significantly large amount of training data, which is highly lacking in the case of the Arabic language. To remedy this, we adopt the semi-supervised co-training approach to the realm of deep learning, which we refer to as deep co-learning. Our deep co-learning approach makes use of a small amount of labeled data, which is augmented with partially labeled data that is automatically generated from Wikipedia. Our approach relies only on word embeddings as features and does not involve any additional feature engineering. Nonetheless, when tested on three different Arabic NER benchmarks, our approach consistently outperforms state-of-the-art Arabic NER approaches, including ones that employ carefully-crafted NLP features. It also consistently outperforms various baselines including purely-supervised deep-learning approaches as well as semi-supervised ones that make use of only unlabeled data such as self-learning and the traditional co-training approach. © 2019, Springer Nature B.V
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
- …
