RESEARCH

NLP

Unsupervised Question Answering by Cloze Translation

July 27, 2019

Abstract

Obtaining training data for Question Answering (QA) is time-consuming and resource-intensive, and existing QA datasets are only available for limited domains and languages. In this work, we explore to what extent high quality training data is actually required for Extractive QA, and investigate the possibility of unsupervised Extractive QA. We approach this problem by first learning to generate context, question and answer triples in an unsupervised manner, which we then use to synthesize Extractive QA training data automatically. To generate such triples, we first sample random context paragraphs from a large corpus of documents and then random noun phrases or named entity mentions from these paragraphs as answers. Next we convert answers in context to “fill-in-the-blank” cloze questions and finally translate them into natural questions. We propose and compare various unsupervised ways to perform cloze-to-natural question translation, including training an unsupervised NMT model using non-aligned corpora of natural questions and cloze questions as well as a rule-based approach. We find that modern QA models can learn to answer human questions surprisingly well using only synthetic training data. We demonstrate that, without using the SQuAD training data at all, our approach achieves 56.4 F1 on SQuAD v1 (64.5 F1 when the answer is a Named entity mention), outperforming early supervised models.

Download the Paper

Related Publications

May 31, 2019

INTEGRITY

Abusive Language Detection with Graph Convolutional Networks | Facebook AI Research

Abuse on the Internet represents a significant societal problem of our time. Previous research on automated abusive language detection in Twitter has shown that community-based profiling of users is a promising technique for this task. However,…

Pushkar Mishra, Marco Del Tredici, Helen Yannakoudakis, Ekaterina Shutova

May 31, 2019

November 02, 2019

NLP

SPEECH & AUDIO

Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack | Facebook AI Research

The detection of offensive language in the context of a dialogue has become an increasingly important application of natural language processing. The detection of trolls in public forums (Galan-García et al., 2016), and the deployment of…

Emily Dinan, Samuel Humeau, Bharath Chintagunta, Jason Weston

November 02, 2019

April 30, 2018

COMPUTER VISION

INTEGRITY

Countering Adversarial Images Using Input Transformations | Facebook AI Research

This paper investigates strategies that defend against adversarial-example attacks on image-classification systems by transforming the inputs before feeding them to the system. Specifically, we study applying image transformations such as…

Chuan Guo, Mayank Rana, Moustapha Cisse, Laurens van der Maaten

April 30, 2018

June 15, 2019

COMPUTER VISION

INTEGRITY

Feature Denoising for Improving Adversarial Robustness | Facebook AI Research

Adversarial attacks to image classification systems present challenges to convolutional networks and opportunities for understanding them. This study suggests that adversarial perturbations on images lead to noise in the features constructed by…

Kaiming He, Yuxin Wu, Laurens van der Maaten, Alan Yuille, Cihang Xie

June 15, 2019

Related Work

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.