Large-scale Simple Question Answering with Memory Networks

2015-06-05 · Antoine Bordes, Nicolas Usunier, Sumit Chopra, Jason Weston

Training large-scale question answering systems is complicated because training sources usually cover a small portion of the range of possible questions. This paper studies the impact of multitask and transfer learning for simple question answering; a setting for which the reasoning required to answer is quite easy, as long as one can retrieve the correct evidence given a question, which can be difficult in large-scale conditions. To this end, we introduce a new dataset of 100k questions that we use in conjunction with existing benchmarks. We conduct our study within the framework of Memory Networks (Weston et al., 2015) because this perspective allows us to eventually scale up to more complex reasoning, and show that Memory Networks can be successfully trained to achieve excellent performance.

📄 PDF Abstract BibTeX arXiv:1506.02075

Code (3)

au1khan/FactQA

aukhanee/FactQA

facebookresearch/ParlAI pytorch

Tasks

Question Answering Transfer Learning

Finding ReMO (Related Memory Object): A Simple Neural Architecture for Text based Reasoning

2018-01-25 · ICLR 2018 1 · Jihyung Moon, Hyochang Yang, Sungzoon Cho

To solve the text-based question and answering task that requires relational reasoning, it is necessary to memorize a large amount of information and find out the question relevant information from the memory. Most appro…

Question Answering Relation Relational Reasoning Relation Network

Visual Question Answering with Memory-Augmented Networks

2017-07-17 · CVPR 2018 6 · Chao Ma, Chunhua Shen, Anthony Dick, Qi Wu 외

In this paper, we exploit a memory-augmented neural network to predict accurate answers to visual questions, even when those answers occur rarely in the training set. The memory network incorporates both internal and ext…

Question Answering Visual Question Answering Visual Question Answering (VQA)

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

2019-03-14 · ACL 2019 7 · Moonsu Han, Minki Kang, Hyunwoo Jung, Sung Ju Hwang

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, which is difficult to solve with exi…

Question Answering Reading Comprehension Scheduling TriviaQA

Hierarchical Memory Networks

2016-05-24 · Sarath Chandar, Sungjin Ahn, Hugo Larochelle, Pascal Vincent 외

Memory networks are neural networks with an explicit memory component that can be both read and written to by the network. The memory is often addressed in a soft way using a softmax function, making end-to-end training …

Hard Attention Question Answering Reinforcement Learning

Explicit Knowledge-based Reasoning for Visual Question Answering

2015-11-09 · Peng Wang, Qi Wu, Chunhua Shen, Anton Van Den Hengel 외

We describe a method for visual question answering which is capable of reasoning about contents of an image on the basis of information extracted from a large-scale knowledge base. The method not only answers natural lan…