08/12/2020

ContraCAT: Contrastive Coreference Analytical Templates for Machine Translation

Dario Stojanovski, Benno Krojer, Denis Peskov, Alexander Fraser

Keywords:

Abstract Paper Similar Papers

Abstract: Recent high scores on pronoun translation using context-aware neural machine translation have suggested that current approaches work well. ContraPro is a notable example of a contrastive challenge set for English→German pronoun translation. The high scores achieved by transformer models may suggest that they are able to effectively model the complicated set of inferences required to carry out pronoun translation. This entails the ability to determine which entities could be referred to, identify which entity a source-language pronoun refers to (if any), and access the target-language grammatical gender for that entity. We first show through a series of targeted adversarial attacks that in fact current approaches are not able to model all of this information well. Inserting small amounts of distracting information is enough to strongly reduce scores, which should not be the case. We then create a new template test set ContraCAT, designed to individually assess the ability to handle the specific steps necessary for successful pronoun translation. Our analyses show that current approaches to context-aware NMT rely on a set of surface heuristics, which break down when translations require real reasoning. We also propose an approach for augmenting the training data, with some improvements.

The video of this talk cannot be embedded. You can watch it here:
https://underline.io/lecture/6321-contracat-contrastive-coreference-analytical-templates-for-machine-translation
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at COLING 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 14:31 
 0
 0
 0
 0
 13:17 
 0
 0
 0
 0
 12:07 
 0
 0
 0
 0
 11:56 
 0
 0
 0
 0
 11:19 
 0
 0
 0
 0
 6:43 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 11:35 
 0
 0
 0
 0
 11:48 
 0
 0
 0
 0
 17:37 
 0
 0
 0
 0
 11:02 
 0
 0
 0
 0
 17:06 
 0
 0
 0
 0
 12:57 
 0
 0
 0
 0
 12:39 
 0
 0
 0
 0
 8:15 
 0
 0
 0
 0
 14:42 
 0
 0
 0
 0
 11:52 
 0
 0
 0
 0
 11:51 
 0
 0
 0
 0
 16:08 
 0
 0
 0
 0
 12:06 
 0
 0
 0
 0
 10:04 
 0
 0
 0
 0
 12:16 
 0
 0
 0
 0
 9:45 
 0
 0
 0
 0
 11:34 
 0
 0
 0
 0
 4:11 
 0
 0
 0
 0
 4:51 
 0
 0
 0
 0
 6:52 
 0
 0
 0
 0
 16:40 
 0
 0
 0
 0
 11:33 
 0
 0
 0
 0
 15:15 
 0
 0
 0
 0
 12:36 
 0
 0
 0
 0
 9:24 
 0
 0
 0
 0
 19:17 
 0
 0
 0
 0
 11:36 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 11:11 
 0
 0
 0
 0
 11:45 
 0
 0
 0
 0
 14:01 
 0
 0
 0
 0
 14:59 
 0
 0
 0
 0
 7:02