PheMT is a phenomenon-wise dataset created to evaluate NMT robustness against linguistic phenomena in Japanese-English UGC translation, with experiments showing major performance drops on certain phenomena.
In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers , pages 1773–1782
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2020 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PheMT: A Phenomenon-wise Dataset for Machine Translation Robustness on User-Generated Contents
PheMT is a phenomenon-wise dataset created to evaluate NMT robustness against linguistic phenomena in Japanese-English UGC translation, with experiments showing major performance drops on certain phenomena.