A Memory Model for Question Answering from Streaming Data Supported by Rehearsal and Anticipation of Coreference Information

Vladimir Araujo, Alvaro Soto, Marie-Francine Moens

Abstract
Existing question answering methods often assume that the input content (e.g., documents or videos) is always accessible to solve the task. Alternatively, memory networks were introduced to mimic the human process of incremental comprehension and compression of the information in a fixed-capacity memory. However, these models only learn how to maintain memory by backpropagating errors in the answers through the entire network. Instead, it has been suggested that humans have effective mechanisms to boost their memorization capacities, such as rehearsal and anticipation. Drawing inspiration from these, we propose a memory model that performs rehearsal and anticipation while processing inputs to memorize important information for solving question answering tasks from streaming data. The proposed mechanisms are applied self-supervised during training through masked modeling tasks focused on coreference information. We validate our model on a short-sequence (bAbI) dataset as well as large-sequence textual (NarrativeQA) and video (ActivityNet-QA) question answering datasets, where it achieves substantial improvements over previous memory network approaches. Furthermore, our ablation study confirms the proposed mechanisms’ importance for memory models.
Anthology ID:
2023.findings-acl.830
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13124–13138
Language:
URL:
https://aclanthology.org/2023.findings-acl.830
DOI:
10.18653/v1/2023.findings-acl.830
Bibkey:
Cite (ACL):
Vladimir Araujo, Alvaro Soto, and Marie-Francine Moens. 2023. A Memory Model for Question Answering from Streaming Data Supported by Rehearsal and Anticipation of Coreference Information. In Findings of the Association for Computational Linguistics: ACL 2023, pages 13124–13138, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
A Memory Model for Question Answering from Streaming Data Supported by Rehearsal and Anticipation of Coreference Information (Araujo et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/proper-vol2-ingestion/2023.findings-acl.830.pdf
PDF Search