DeepAI AI Chat
Log In Sign Up

Why Robust Natural Language Understanding is a Challenge

by   Marco Casadio, et al.
University of Strathclyde
Heriot-Watt University

With the proliferation of Deep Machine Learning into real-life applications, a particular property of this technology has been brought to attention: Neural Networks notoriously present low robustness and can be highly sensitive to small input perturbations. Recently, many methods for verifying networks' general properties of robustness have been proposed, but they are mostly applied in Computer Vision. In this paper we propose a Verification method for Natural Language Understanding classification based on larger regions of interest, and we discuss the challenges of such task. We observe that, although the data is almost linearly separable, the verifier does not output positive results and we explain the problems and implications.


page 1

page 2

page 3

page 4


Natural Language Understanding with Distributed Representation

This is a lecture note for the course DS-GA 3001 <Natural Language Under...

The Unstoppable Rise of Computational Linguistics in Deep Learning

In this paper, we trace the history of neural networks applied to natura...

The Deep Learning Revolution and Its Implications for Computer Architecture and Chip Design

The past decade has seen a remarkable series of advances in machine lear...

Multi-task learning to improve natural language understanding

Recently advancements in sequence-to-sequence neural network architectur...

An Analysis of Negation in Natural Language Understanding Corpora

This paper analyzes negation in eight popular corpora spanning six natur...

SNEAK: Synonymous Sentences-Aware Adversarial Attack on Natural Language Video Localization

Natural language video localization (NLVL) is an important task in the v...

VASTA: A Vision and Language-assisted Smartphone Task Automation System

We present VASTA, a novel vision and language-assisted Programming By De...