Are ambiguous conjunctions problematic for machine translation?

Maja Popović, Sheila Castilho


Abstract
The translation of ambiguous words still poses challenges for machine translation. In this work, we carry out a systematic quantitative analysis regarding the ability of different machine translation systems to disambiguate the source language conjunctions “but” and “and”. We evaluate specialised test sets focused on the translation of these two conjunctions. The test sets contain source languages that do not distinguish different variants of the given conjunction, whereas the target languages do. In total, we evaluate the conjunction “but” on 20 translation outputs, and the conjunction “and” on 10. All machine translation systems almost perfectly recognise one variant of the target conjunction, especially for the source conjunction “but”. The other target variant, however, represents a challenge for machine translation systems, with accuracy varying from 50% to 95% for “but” and from 20% to 57% for “and”. The major error for all systems is replacing the correct target variant with the opposite one.
Anthology ID:
R19-1111
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
Month:
September
Year:
2019
Address:
Varna, Bulgaria
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
959–966
Language:
URL:
https://aclanthology.org/R19-1111
DOI:
10.26615/978-954-452-056-4_111
Bibkey:
Cite (ACL):
Maja Popović and Sheila Castilho. 2019. Are ambiguous conjunctions problematic for machine translation?. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 959–966, Varna, Bulgaria. INCOMA Ltd..
Cite (Informal):
Are ambiguous conjunctions problematic for machine translation? (Popović & Castilho, RANLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/R19-1111.pdf