Despite a multitude of empirical studies, little consensus exists on whether neural networks are able to generalise compositionally, a controversy that, in part, stems from a lack of agreement about what it means for a neural model to be compositional. As a response to this controversy, we present a set of tests that provide a bridge between, on the one hand, the vast amount of linguistic and philosophical theory about compositionality and, on the other, the successful neural models of language. We collect different interpretations of compositionality and translate them into five theoretically grounded tests that are formulated on a task-independent level. In particular, we provide tests to investigate (i) if models systematically recombine known parts and rules (ii) if models can extend their predictions beyond the length they have seen in the training data (iii) if models' composition operations are local or global (iv) if models' predictions are robust to synonym substitutions and (v) if models favour rules or exceptions during training. To demonstrate the usefulness of this evaluation paradigm, we instantiate these five tests on a highly compositional data set which we dub PCFG SET and apply the resulting tests to three popular sequence-to- sequence models: a recurrent, a convolution based and a transformer model. We provide an in depth analysis of the results, that uncover the strengths and weaknesses of these three architectures and point to potential areas of improvement.

To cooperate with humans effectively, virtual agents need to be able to understand and execute language instructions. A typical setup to achieve this is with a scripted teacher which guides a virtual agent using language instructions. However, such setup has clear limitations in scalability and, more importantly, it is not interactive. Here, we introduce an autonomous agent that uses discrete communication to interactively guide other agents to navigate and act on a simulated environment. The developed communication protocol is trainable, emergent and requires no additional supervision. The emergent language speeds up learning of new agents, it generalizes across incrementally more difficult tasks and, contrary to most other emergent languages, it is highly interpretable. We demonstrate how the emitted messages correlate with particular actions and observations, and how new agents become less dependent on this guidance as training progresses. By exploiting the correlations identified in our analysis, we manage to successfully address the agents in their own language.

Can neural nets learn logic? We approach this classic question with current methods, and demonstrate that recurrent neural networks can learn to recognize first order logical entailment relations between expressions. We define an artificial language in first-order predicate logic, generate a large dataset of sample 'sentences', and use an automatic theorem prover to infer the relation between random pairs of such sentences. We describe a Siamese neural architecture trained to predict the logical relation, and experiment with recurrent and recursive networks. Siamese Recurrent Networks are surprisingly successful at the entailment recognition task, reaching near perfect performance on novel sentences (consisting of known words), and even outperforming recursive networks. We report a series of experiments to test the ability of the models to perform compositional generalization. In particular, we study how they deal with sentences of unseen length, and sentences containing unseen words. We show that set-ups using LSTMs and GRUs obtain high scores on these tests, demonstrating a form of compositionality.