| 1 |
Replacing Linguists with Dummies: A Serious Need for Trivial Baselines in Multi-Task Neural Machine Translation
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 113, Iss 1, Pp 31-40 (2019) (2019)
|
|
Abstract:
Recent developments in machine translation experiment with the idea that a model can improve the translation quality by performing multiple tasks, e.g., translating from source to target and also labeling each source word with syntactic information. The intuition is that the network would generalize knowledge over the multiple tasks, improving the translation performance, especially in low resource conditions. We devised an experiment that casts doubt on this intuition. We perform similar experiments in both multi-decoder and interleaving setups that label each target word either with a syntactic tag or a completely random tag. Surprisingly, we show that the model performs nearly as well on uncorrelated random tags as on true syntactic tags. We hint some possible explanations of this behavior.
|
|
Keyword:
Computational linguistics. Natural language processing; P98-98.5
|
|
URL: https://doaj.org/article/7a7c7ec0f58343ffa605912b26a6d2a6
https://doi.org/10.2478/pralin-2019-0005
|
|
BASE
|
|
Hide details
|
|
|
|
|
