Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks

02/19/2015
by   Jason Weston, et al.
Facebook
0

One long-term goal of machine learning research is to produce methods that are applicable to reasoning and natural language, in particular building an intelligent dialogue agent. To measure progress towards that goal, we argue for the usefulness of a set of proxy tasks that evaluate reading comprehension via question answering. Our tasks measure understanding in several ways: whether a system is able to answer questions via chaining facts, simple induction, deduction and many more. The tasks are designed to be prerequisites for any system that aims to be capable of conversing with a human. We believe many existing learning systems can currently not solve them, and hence our aim is to classify these tasks into skill sets, so that researchers can identify (and then rectify) the failings of their systems. We also extend and improve the recently introduced Memory Networks model, and show it is able to solve some, but not all, of the tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

08/27/2020

Relation/Entity-Centric Reading Comprehension

Constructing a machine that understands human language is one of the mos...
12/19/2017

The NarrativeQA Reading Comprehension Challenge

Reading comprehension (RC)---in contrast to information retrieval---requ...
09/12/2018

Knowledge Based Machine Reading Comprehension

Machine reading comprehension (MRC) requires reasoning about both the kn...
01/14/2015

Hard to Cheat: A Turing Test based on Answering Questions about Images

Progress in language and image understanding by machines has sparkled th...
06/20/2018

Jack the Reader - A Machine Reading Framework

Many Machine Reading and Natural Language Understanding tasks require re...
04/20/2016

Dialog-based Language Learning

A long-term goal of machine learning research is to build an intelligent...
10/19/2022

Two-Turn Debate Doesn't Help Humans Answer Hard Reading Comprehension Questions

The use of language-model-based question-answering systems to aid humans...

Code Repositories

bAbI-tasks

Task generation for testing text understanding and reasoning


view repo

bAbi_QA

Solving Question-Answering Problem Using Deep Learning


view repo

QA_RNN

Question Answering Using Attentive Reader and Recurrent Neural Networks


view repo

Memory-Networks

Re-implementation of Memory Networks (MemNN) paper of Facebook AI Research Lab.


view repo

QuestionAnsweringBasedSystem

This is an implementation Of Question Answering System on bAbi DataSet


view repo

Please sign up or login with your details

Forgot password? Click here to reset