Knowledgeable reader: Enhancing cloze-style reading comprehension with external commonsense knowledge
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 knowled...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Chapter/Article Conference Paper |
| Language: | English |
| Published: |
July 2018
|
| In: |
The 56th Annual Meeting of the Association for Computational Linguistics - proceedings of the conference ; Vol. 1: Long papers
Year: 2018, Pages: 821-832 |
| DOI: | 10.18653/v1/P18-1076 |
| Online Access: | Verlag, kostenfrei, Volltext: https://doi.org/10.18653/v1/P18-1076 Verlag, kostenfrei, Volltext: https://aclanthology.org/P18-1076 
|
| Author Notes: | Todor Mihaylov and Anette Frank |
| Summary: | 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. |
|---|---|
| Item Description: | Gesehen am 15.07.2024 |
| Physical Description: | Online Resource |
| ISBN: | 9781948087322 |
| DOI: | 10.18653/v1/P18-1076 |