08/12/2020

Understanding the effects of word-level linguistic annotations in under-resourced neural machine translation

Víctor M. Sánchez-Cartagena, Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez

Keywords:

Abstract Paper Similar Papers

Abstract: This paper studies the effects of word-level linguistic annotations in under-resourced neural machine translation, for which there is incomplete evidence in the literature. The study covers eight language pairs, different training corpus sizes, two architectures, and three types of annotation: dummy tags (with no linguistic information at all), part-of-speech tags, and morpho-syntactic description tags, which consist of part of speech and morphological features. These linguistic annotations are interleaved in the input or output streams as a single tag placed before each word. In order to measure the performance under each scenario, we use automatic evaluation metrics and perform automatic error classification. Our experiments show that, in general, source-language annotations are helpful and morpho-syntactic descriptions outperform part of speech for some language pairs. On the contrary, when words are annotated in the target language, part-of-speech tags systematically outperform morpho-syntactic description tags in terms of automatic evaluation metrics, even though the use of morpho-syntactic description tags improves the grammaticality of the output. We provide a detailed analysis of the reasons behind this result.

The video of this talk cannot be embedded. You can watch it here:
https://underline.io/lecture/6283-understanding-the-effects-of-word-level-linguistic-annotations-in-under-resourced-neural-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
 1
 4:49 
 0
 0
 0
 0
 15:22 
 0
 0
 0
 0
 9:11 
 0
 0
 0
 0
 13:44 
 0
 0
 0
 0
 13:01 
 0
 0
 0
 0
 14:31 
 0
 0
 0
 0
 12:57 
 0
 0
 0
 0
 10:48 
 0
 0
 0
 0
 4:00 
 0
 0
 0
 0
 14:09 
 0
 0
 0
 0
 12:23 
 0
 0
 0
 0
 14:04 
 0
 0
 0
 0
 5:40 
 0
 0
 0
 0
 10:27 
 0
 0
 0
 0
 6:43 
 0
 0
 0
 0
 11:45 
 0
 0
 0
 0
 9:54 
 0
 0
 0
 0
 12:24 
 0
 0
 0
 0
 19:17 
 0
 0
 0
 0
 8:15 
 0
 0
 0
 0
 11:47 
 0
 0
 0
 0
 10:04 
 0
 0
 0
 0
 19:35 
 0
 0
 0
 0
 13:57 
 0
 0
 0
 0
 14:50 
 0
 0
 0
 0
 12:23 
 0
 0
 0
 0
 7:09 
 0
 0
 0
 0
 11:19 
 0
 0
 0
 0
 8:39 
 0
 0
 0
 0
 7:13 
 0
 0
 0
 0
 5:56 
 0
 0
 0
 0
 7:48 
 0
 0
 0
 0
 6:04 
 0
 0
 0
 0
 4:38 
 0
 0
 0
 0
 12:06 
 0
 0
 0
 0
 9:45 
 0
 0
 0
 0
 14:39 
 0
 0
 0
 0
 10:02 
 0
 0
 0
 0
 7:04 
 0
 0
 0
 0
 11:58