Memory Graph Networks for Explainable Memory-grounded Question Answering
| Autor: | Anuj Kumar, Seungwhan Moon, Pararth Shah, Rajen Subba |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
business.industry 02 engineering and technology computer.software_genre Graph 03 medical and health sciences 0302 clinical medicine Scripting language 030221 ophthalmology & optometry 0202 electrical engineering electronic engineering information engineering Question answering 020201 artificial intelligence & image processing Artificial intelligence business Episodic memory computer |
| Zdroj: | CoNLL |
| DOI: | 10.18653/v1/k19-1068 |
| Popis: | We introduce Episodic Memory QA, the task of answering personal user questions grounded on memory graph (MG), where episodic memories and related entity nodes are connected via relational edges. We create a new benchmark dataset first by generating synthetic memory graphs with simulated attributes, and by composing 100K QA pairs for the generated MG with bootstrapped scripts. To address the unique challenges for the proposed task, we propose Memory Graph Networks (MGN), a novel extension of memory networks to enable dynamic expansion of memory slots through graph traversals, thus able to answer queries in which contexts from multiple linked episodes and external knowledge are required. We then propose the Episodic Memory QA Net with multiple module networks to effectively handle various question types. Empirical results show improvement over the QA baselines in top-k answer prediction accuracy in the proposed task. The proposed model also generates a graph walk path and attention vectors for each predicted answer, providing a natural way to explain its QA reasoning. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|