Meta Answering for Machine Reading

11/11/2019
by   Benjamin Borschinger, et al.
16

We investigate a framework for machine reading, inspired by real world information-seeking problems, where a meta question answering system interacts with a black box environment. The environment encapsulates a competitive machine reader based on BERT, providing candidate answers to questions, and possibly some context. To validate the realism of our formulation, we ask humans to play the role of a meta-answerer. With just a small snippet of text around an answer, humans can outperform the machine reader, improving recall. Similarly, a simple machine meta-answerer outperforms the environment, improving both precision and recall on the Natural Questions dataset. The system relies on joint training of answer scoring and the selection of conditioning information.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/28/2019

Interactive Language Learning by Question Answering

Humans observe and interact with the world to acquire knowledge. However...
research
08/28/2018

Interpretation of Natural Language Rules in Conversational Machine Reading

Most work in machine reading focuses on question answering problems wher...
research
08/21/2018

QuAC : Question Answering in Context

We present QuAC, a dataset for Question Answering in Context that contai...
research
10/29/2018

ReviewQA: a relational aspect-based opinion reading dataset

Deep reading models for question-answering have demonstrated promising p...
research
11/22/2017

Visual Question Answering as a Meta Learning Task

The predominant approach to Visual Question Answering (VQA) demands that...
research
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...
research
05/19/2023

Solving NLP Problems through Human-System Collaboration: A Discussion-based Approach

Humans work together to solve common problems by having discussions, exp...

Please sign up or login with your details

Forgot password? Click here to reset