TL;DR
This study compares offline and online neural machine translation models, specifically convolutional Pervasive Attention and Transformer, assessing how online decoding constraints affect translation quality for English-German and German-English pairs through human evaluation.
Contribution
It provides an in-depth analysis of the impact of online decoding constraints on NMT quality, highlighting strengths and weaknesses of each model in real-time translation scenarios.
Findings
Transformers perform better offline but face challenges online.
Online decoding constraints reduce translation quality for both models.
German-English translation is more sensitive to latency constraints.
Abstract
We conduct in this work an evaluation study comparing offline and online neural machine translation architectures. Two sequence-to-sequence models: convolutional Pervasive Attention (Elbayad et al. 2018) and attention-based Transformer (Vaswani et al. 2017) are considered. We investigate, for both architectures, the impact of online decoding constraints on the translation quality through a carefully designed human evaluation on English-German and German-English language pairs, the latter being particularly sensitive to latency constraints. The evaluation results allow us to identify the strengths and shortcomings of each model when we shift to the online setup.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsLinear Layer · Absolute Position Encodings · Position-Wise Feed-Forward Layer · Residual Connection · Label Smoothing · Multi-Head Attention · Adam · *Communicated@Fast*How Do I Communicate to Expedia? · Dropout · Byte Pair Encoding
