Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data

03/14/2019
by   Moonsu Han, et al.
0

We consider a novel question answering (QA) task where the machine needs to read from large streaming data (long documents or videos) without knowing when the questions will be given, in which case the existing QA methods fail due to lack of scalability. To tackle this problem, we propose a novel end-to-end reading comprehension method, which we refer to as Episodic Memory Reader (EMR) that sequentially reads the input contexts into an external memory, while replacing memories that are less important for answering unseen questions. Specifically, we train an RL agent to replace a memory entry when the memory is full in order to maximize its QA accuracy at a future timepoint, while encoding the external memory using the transformer architecture to learn representations that considers relative importance between the memory entries. We validate our model on a real-world large-scale textual QA task (TriviaQA) and a video QA task (TVQA), on which it achieves significant improvements over rule-based memory scheduling policies or an RL-based baseline that learns the query-specific importance of each memory independently.

READ FULL TEXT

page 8

page 13

page 14

research
12/11/2018

Learning What to Remember: Long-term Episodic Memory Networks for Learning from Streaming Data

Current generation of memory-augmented neural networks has limited scala...
research
05/12/2023

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

Existing question answering methods often assume that the input content ...
research
09/25/2021

More Than Reading Comprehension: A Survey on Datasets and Metrics of Textual Question Answering

Textual Question Answering (QA) aims to provide precise answers to user'...
research
10/19/2020

Technical Question Answering across Tasks and Domains

Building automatic technical support system is an important yet challeng...
research
03/11/2017

Ask Me Even More: Dynamic Memory Tensor Networks (Extended Model)

We examine Memory Networks for the task of question answering (QA), unde...
research
09/05/2018

TVQA: Localized, Compositional Video Question Answering

Recent years have witnessed an increasing interest in image-based questi...
research
06/09/2016

Key-Value Memory Networks for Directly Reading Documents

Directly reading documents and being able to answer questions from them ...

Please sign up or login with your details

Forgot password? Click here to reset