Analyzing Neural MT Search and Model Performance

In this paper, we offer an in-depth analysis about the modeling and search performance. We address the question if a more complex search algorithm is necessary. Furthermore, we investigate the question if more complex models which might only be applicable during rescoring are promising. By separatin...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2017-08
Main Authors: Niehues, Jan, Cho, Eunah, Thanh-Le, Ha, Waibel, Alex
Format: Article
Language:English
Subjects:
Modelling
Search algorithms
Translations
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we offer an in-depth analysis about the modeling and search performance. We address the question if a more complex search algorithm is necessary. Furthermore, we investigate the question if more complex models which might only be applicable during rescoring are promising. By separating the search space and the modeling using \(n\)-best list reranking, we analyze the influence of both parts of an NMT system independently. By comparing differently performing NMT systems, we show that the better translation is already in the search space of the translation systems with less performance. This results indicate that the current search algorithms are sufficient for the NMT systems. Furthermore, we could show that even a relatively small \(n\)-best list of \(50\) hypotheses already contain notably better translations.
ISSN:2331-8422