Grégoire Winterstein
Université du Québec à Montréal
38 Papers
105 Citations
Grégoire Winterstein is an academic researcher from Université du Québec à Montréal. The author has contributed to research in topics: Sentiment analysis & Argumentative. The author has an hindex of 9, co-authored 36 publications. Previous affiliations of Grégoire Winterstein include Aix-Marseille University & University of Hong Kong.
Chat about Author
Papers
Sentic patterns: dependency-based rules for concept-level sentiment analysis
TL;DR: The authors proposed a concept-level sentiment analysis that merges linguistics, common-sense computing, and machine learning for improving the accuracy of tasks such as polarity detection, by allowing sentiments to flow from concept to concept based on the dependency relation of the input sentence, in particular, achieving a better understanding of the contextual role of each concept within the sentence and, hence, obtaining a polarity detector that outperforms state-of-the-art statistical methods.
370
Empirical constraints on accounts of Too
Grégoire Winterstein,Henk Zeevat +1 more
TL;DR: The paper argues that there are also optional uses and cases where there is a proper antecedent for too, but too is better avoided, and suggests some solutions.
19
•Proceedings Article
Cifu: a Frequency Lexicon of Hong Kong Cantonese.
Regine Lai,Grégoire Winterstein +1 more
- 01 May 2020
TL;DR: Cifu is of use for NLP applications and the design and analysis of psycholinguistics experiments on HKC, and it is found that the lexical diversity of the child-directed speech genre is particularly low, compared to a size-matched written corpus.
15
Construction et exploitation d'un corpus français pour l'analyse de sentiment
Marc Vincent,Grégoire Winterstein +1 more
- 01 Jan 2013
TL;DR: This work applies machine learning techniques to automatically predict whether a text is positive or negative (the opinion classification task) and briefly evaluates the merits of applying feature selection algorithms to the authors' models.
14
Testing Epistemic Injustice
Elin McCready,Grégoire Winterstein +1 more
- 11 Dec 2019
TL;DR: The authors argue that masculine sources benefit from more charitable assumptions than feminine ones, and present the results of a fine-grained categorization task to support their claim about charity, i.e. that a masculine source can more easily claim competence about a topic categorized as feminine, whereas the converse appears less true.