“Look, some Green Circles!”: Learning to Quantify from Images

By Ionut-Teodor Sorodoc, Angeliki Lazaridou, Gemma Boleda, Aurélie Herbelot, Sandro Pezzelle, Raffaella Bernardi. 2016

18 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Experimental and Cognitive Psychology, Multimodal Learning, Computational Linguistics & Semantics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Alexander Kuhnle
2. Ann A. Copestake
3. Noah D. Goodman
4. Jesse Mu

In Computer Vision and Pattern Recognition

1. Ann A. Copestake
2. Alexander Kuhnle
3. Noah D. Goodman
4. Jesse Mu

In Multimodal Learning

1. Ann A. Copestake
2. Alexander Kuhnle
3. Noah D. Goodman
4. Jesse Mu

Citations in the corpus

• ShapeWorld - A new test methodology for multimodal language understanding (2017, background): “Bowman et al. (2015) and Sorodoc et al. (2016) are more similar to our work in focusing on specific linguistic aspects.”