Ask Me Even More: Dynamic Memory Tensor Networks (Extended Model)
This addresses QA performance in data-scarce, weakly supervised scenarios, though it appears incremental as an extension of existing memory network architectures.
The authors tackled question answering with scarce training data and weak supervision by extending Dynamic Memory Networks with improved attention mechanisms, achieving over 80% improvement over baseline DMN and 20% more tasks passed than state-of-the-art on the bAbi dataset.
We examine Memory Networks for the task of question answering (QA), under common real world scenario where training examples are scarce and under weakly supervised scenario, that is only extrinsic labels are available for training. We propose extensions for the Dynamic Memory Network (DMN), specifically within the attention mechanism, we call the resulting Neural Architecture as Dynamic Memory Tensor Network (DMTN). Ultimately, we see that our proposed extensions results in over 80% improvement in the number of task passed against the baselined standard DMN and 20% more task passed compared to state-of-the-art End-to-End Memory Network for Facebook's single task weakly trained 1K bAbi dataset.