Compositional Generalization in Grounded Language Learning via Induced Model Sparsity
We provide a study of how induced model sparsity can help achieve compositional generalization and better sample efficiency in grounded language learning problems. We consider simple language-conditioned navigation problems in a grid world environment with disentangled observations. We show that standard neural architectures do not always yield compositional generalization. To address this, we design an agent that contains a goal identification module that encourages sparse correlations between words in the instruction and attributes of objects, composing them together to find the goal. The output of the goal identification module is the input to a value iteration network planner. Our agent maintains a high level of performance on goals containing novel combinations of properties even when learning from a handful of demonstrations. We examine the internal representations of our agent and find the correct correspondences between words in its dictionary and attributes in the environment.
Code (1)
Tasks
Grounded language learningSimilar Papers 제목 키워드 기반
Inducing Transformer’s Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks
Systematic compositionality is an essential mechanism in human language, allowing the recombination of known parts to create novel expressions. However, existing neural models have been shown to lack this basic ability i…
Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks
Systematic compositionality is an essential mechanism in human language, allowing the recombination of known parts to create novel expressions. However, existing neural models have been shown to lack this basic ability i…
A Benchmark for Systematic Generalization in Grounded Language Understanding
Humans easily interpret expressions that describe unfamiliar situations composed from familiar parts ("greet the pink brontosaurus by the ferris wheel"). Modern neural networks, by contrast, struggle to interpret novel c…
Systematic GeneralizationRecursive Decoding: A Situated Cognition Approach to Compositional Generation in Grounded Language Understanding
Compositional generalization is a troubling blind spot for neural language models. Recent efforts have presented techniques for improving a model's ability to encode novel combinations of known inputs, but less work has …
DecoderWhen Can Transformers Ground and Compose: Insights from Compositional Generalization Benchmarks
Humans can reason compositionally whilst grounding language utterances to the real world. Recent benchmarks like ReaSCAN use navigation tasks grounded in a grid world to assess whether neural models exhibit similar capab…
Compositional Generalization (AVG)