CompGuessWhat?!: A Multi-task Evaluation Framework for Grounded Language Learning
This work addresses the need for better evaluation in grounded language learning, though it is incremental as it builds on existing datasets and methods.
The authors tackled the problem of evaluating grounded language learning models by introducing GROLLA, a multi-task evaluation framework, and the CompGuessWhat?! dataset, which revealed that current models achieve only 44.27 average F1 in attribute prediction and 50.06% accuracy in zero-shot scenarios.
Approaches to Grounded Language Learning typically focus on a single task-based final performance measure that may not depend on desirable properties of the learned hidden representations, such as their ability to predict salient attributes or to generalise to unseen situations. To remedy this, we present GROLLA, an evaluation framework for Grounded Language Learning with Attributes with three sub-tasks: 1) Goal-oriented evaluation; 2) Object attribute prediction evaluation; and 3) Zero-shot evaluation. We also propose a new dataset CompGuessWhat?! as an instance of this framework for evaluating the quality of learned neural representations, in particular concerning attribute grounding. To this end, we extend the original GuessWhat?! dataset by including a semantic layer on top of the perceptual one. Specifically, we enrich the VisualGenome scene graphs associated with the GuessWhat?! images with abstract and situated attributes. By using diagnostic classifiers, we show that current models learn representations that are not expressive enough to encode object attributes (average F1 of 44.27). In addition, they do not learn strategies nor representations that are robust enough to perform well when novel scenes or objects are involved in gameplay (zero-shot best accuracy 50.06%).