stat946w18/Synthetic and natural noise both break neural machine translation

Introduction

• Humans have surprisingly robust language processing systems which can easily overcome typos, e.g.

Aoccdrnig to a rscheearch at Cmabrigde Uinervtisy, it deosn't mttaer in waht oredr the ltteers in a wrod are, the olny iprmoetnt tihng is taht the frist and lsat ltteer be at the rghit pclae.

• A person's ability to read this text comes as no surprise to the Psychology literature

   	** Saberi \& Perrott (1999) found that this robustness extends to audio as well.
   	
   	** Rayner et al. (2006) found that in noisier settings reading comprehension only slowed by 11 \%.
   	
   	** McCusker et al. (1981) found that the common case of swapping letters could often go unnoticed by the reader.
   	
   	** Mayall et al (1997) shows that we rely on word shape.
   	
   	** Reicher, 1969; Pelli et al., (2003) found that we can switch between whole word recognition but the first and last letter positions are required to stay constant for comprehension