1 |
Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
The Multilingual TEDx Corpus for Speech Recognition and Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Simultaneous Speech Translation for Live Subtitling: from Delay to Display ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Speechformer: Reducing Information Loss in Direct Speech Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Is “moby dick” a Whale or a Bird? Named Entities and Terminology in Speech Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Speechformer: Reducing Information Loss in Direct Speech Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference? ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Between Flexibility and Consistency: Joint Generation of Captions and Subtitles ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Low Resource Neural Machine Translation: A Benchmark for Five African Languages ...
|
|
|
|
Abstract:
Recent advents in Neural Machine Translation (NMT) have shown improvements in low-resource language (LRL) translation tasks. In this work, we benchmark NMT between English and five African LRL pairs (Swahili, Amharic, Tigrigna, Oromo, Somali [SATOS]). We collected the available resources on the SATOS languages to evaluate the current state of NMT for LRLs. Our evaluation, comparing a baseline single language pair NMT model against semi-supervised learning, transfer learning, and multilingual modeling, shows significant performance improvements both in the En-LRL and LRL-En directions. In terms of averaged BLEU score, the multilingual approach shows the largest gains, up to +5 points, in six out of ten translation directions. To demonstrate the generalization capability of each model, we also report results on multi-domain test sets. We release the standardized experimental data and the test sets for future works addressing the challenges of NMT in under-resourced settings, in particular for the SATOS ... : Accepted for AfricaNLP workshop at ICLR 2020 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2003.14402 https://arxiv.org/abs/2003.14402
|
|
BASE
|
|
Hide details
|
|
|
|