كتاب إلكتروني
Imparare a quantificare guardando
العنوان: | Imparare a quantificare guardando |
---|---|
المؤلفون: | Pezzelle, Sandro, Sorodoc, Ionut, Herbelot, Aurelie, Bernardi, Raffaella |
المصدر: | Accademia University PressOpenAIRE. |
بيانات النشر: | Accademia University Press, 2017-07-26. |
سنة النشر: | 2017 |
وصف مادي: | 237-242 |
مصطلحات موضوعية: | LNP, Language & Linguistics (General), Computational Linguistics, natural language, experimental methodologies, Linguistica Computazionale, linguaggio naturale, metodologie sperimentali, Linguistique Computationelle, langage naturel, méthodes expérimentales |
الوصف: | In this paper, we focus on linguistic questions over images which may be answered with a quantifier (e.g. How many dogs are black? Some/most/all of them, etc.). We show that in order to learn to quantify, a multimodal model has to obtain a genuine understanding of linguistic and visual inputs and of their interaction. We propose a model that extracts a fuzzy representation of the set of the queried objects (e.g. dogs) and of the queried property in relation to that set (e.g. black with respect to dogs), outputting the appropriate quantifier for that relation. In questo lavoro studiamo le domande del tipo “Quanti cani sono neri?”, la cui risposta è un quantificatore (es. “alcuni”/”tutti”/”nessuno”). Mostriamo che al fine di imparare a quantificare, un modello multimodale deve ottenere una rappresentazione profonda della domanda linguistica, dell’immagine e della loro interazione. Proponiamo un modello che estrae una rappresentazione approssimativa dell’insieme degli oggetti e della proprietà sui quali verte la domanda. |
نوع الوثيقة: | Chapter |
اللغة: | Italian |
ردمك: | 978-88-99982-54-6 |
Relation: | http://books.openedition.org/aaccademia/basictei/1823; http://books.openedition.org/aaccademia/tei/1823 |
DOI: | 10.4000/books.aaccademia.1823 |
URL الوصول: | http://books.openedition.org/aaccademia/1823 |
حقوق: | CC BY-NC-ND 3.0 |
رقم الأكسشن: | edsrev.40E338B3 |
قاعدة البيانات: | Openedition.org |
كن أول من يترك تعليقا!