How Can Memory-Augmented Neural Networks Pass a False-Belief Task?

By Erin Grant, Aida Nematzadeh, T. Griffiths. 2017

35 citations recorded by the source corpus.

Subfields: Model Architectures, Cognitive Science & Psychology

How researchers see this paper

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

In Model Architectures

1. Matt Le
2. Maximilian Nickel
3. Y-Lan Boureau
4. Erin Grant
5. T. Griffiths
6. Aida Nematzadeh

In Cognitive Science & Psychology

1. T. Griffiths
2. Matt Le
3. Maximilian Nickel
4. Y-Lan Boureau
5. Alison Gopnik
6. Aida Nematzadeh
7. Josh Tenenbaum
8. Peter Carruthers

Citations in the corpus

• Evaluating Theory of Mind in Question Answering (2018, methodology): “To address this, Grant et al. (2017) propose the Multiple Observer model that integrates MemN2N with individual memory modules for each agent in the story. An agent’s memory only receives the sentences for which the agent is present and observes the world. Their model has an additional attention fun”
• Revisiting the Evaluation of Theory of Mind through Question Answering (2019, methodology): “Psychology Tests as AI Benchmarks Grant et al. (2017) cast the aforementioned experiments as question answering tasks and proposed to create a bAbi-style dataset (Weston et al., 2016) to evaluate theory of mind in artificial intelligence models.”