2026-04-14T02:45:24Zhttps://recercat.cat/oai/request

oai:recercat.cat:10230/327032025-12-20T16:56:06Zcom_2072_6col_2072_452952

00925njm 22002777a 4500 dc Boleda, Gemma author Sorodoc, Ionut-Teodor author Lazaridou, Angeliki author Herbelot, Aurélie author Pezzelle, Sandro author Bernardi, Raffaella author 2017-08-25T17:17:10Z 2017-08-25T17:17:10Z 2016 In this paper, we investigate whether a neural network model can learn the meaning of natural language quantifiers (no,some and all) from their use in visual contexts. We show that memory networks perform well in this task, and that explicit counting is not necessary to the system’s performance, supporting psycholinguistic evidence on the acquisition of quantifiers. This project has received funding from the European Unions Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 655577 (LOVe); ERC 2011 Starting Independent Research Grant n. 283554 (COMPOSES). Language and vision Grounding Quantification Distributed representations Semantics Computational semantics Computational Linguistics Natural Language Processing “Look, some green circles!”: learning to quantify from images