The red one!: On learning to refer to things based on discriminative properties
By Angeliki Lazaridou, Ngoc-Quan Pham, Marco Baroni. 2016
16 citations recorded by the source corpus.
As a first step towards agents learning to communicate about their visual environment, we propose a system that, given visual representations of a referent (cat) and a context (sofa), identifies their discriminative attributes, i.e., properties that distinguish them (has_tail). Moreover, despite the lack of direct supervision at the attribute level, the model learns to assign plausible attributes to objects (sofa-has_cushion). Finally, we present a preliminary experiment confirming the referential success of the predicted discriminative attributes.
Subfields: Artificial Intelligence, Natural Language Processing
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
- Yejin Choi
- Mohit Bansal
- Luke S. Zettlemoyer
- Percy Liang
- Jacob Andreas
- Graham Neubig
- Jianfeng Gao
- Kyunghyun Cho
In Natural Language Processing
- Mohit Bansal
- Yejin Choi
- Graham Neubig
- Mirella Lapata
- Richard Socher
- Jacob Andreas
- Luke S. Zettlemoyer
- Christopher D. Manning
Citations in the corpus
- Experience Grounds Language (2020, background): “Importantly, this is not a new trend (Chen and Mooney, 2008; Feng and La-pata, 2010; Bruni et al., 2014; Lazaridou et al., 2016), and task and model design can fail to require sensory perception (Thomason et al., 2019a).”