Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge
This addresses reading comprehension for AI systems by enhancing inference with external knowledge, though it is incremental as it builds on existing neural models.
The paper tackles cloze-style reading comprehension by integrating external commonsense knowledge via a key-value memory, improving results over a strong baseline on a hard Common Nouns dataset.
We introduce a neural reading comprehension model that integrates external commonsense knowledge, encoded as a key-value memory, in a cloze-style setting. Instead of relying only on document-to-question interaction or discrete features as in prior work, our model attends to relevant external knowledge and combines this knowledge with the context representation before inferring the answer. This allows the model to attract and imply knowledge from an external knowledge source that is not explicitly stated in the text, but that is relevant for inferring the answer. Our model improves results over a very strong baseline on a hard Common Nouns dataset, making it a strong competitor of much more complex models. By including knowledge explicitly, our model can also provide evidence about the background knowledge used in the RC process.