Revisiting Negation in Neural Machine Translation
In this paper, we evaluate the translation of negation both automatically and manually, in English–German (EN–DE) and English– Chinese (EN–ZH). We show that the ability of neural machine translation (NMT) models to translate negation has improved with deeper and more advanced network...
Main Authors: | Gongbo Tang, Philipp Rönchen, Rico Sennrich, Joakim Nivre |
---|---|
Format: | Article |
Language: | English |
Published: |
The MIT Press
2021-01-01
|
Series: | Transactions of the Association for Computational Linguistics |
Online Access: | https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00395/106793/Revisiting-Negation-in-Neural-Machine-Translation |
Similar Items
-
Schrödinger's tree—On syntax and neural language models
by: Artur Kulmizev, et al.
Published: (2022-10-01) -
Revisiting Multi-Domain Machine Translation
by: MinhQuang Pham, et al.
Published: (2021-01-01) -
What Should/Do/Can LSTMs Learn When Parsing Auxiliary Verb
Constructions?
by: Miryam de Lhoneux, et al.
Published: (2021-12-01) -
Revisiting Back-Translation for Low-Resource Machine Translation Between Chinese and Vietnamese
by: Hongzheng Li, et al.
Published: (2020-01-01) -
Nucleus Composition in Transition-based Dependency Parsing
by: Joakim Nivre, et al.
Published: (2022-07-01)