Translating a Language You Don’t Know In the Chinese Room

Ulf Hermjakob, Jonathan May, Michael Pust, Kevin Knight


Abstract
In a corruption of John Searle’s famous AI thought experiment, the Chinese Room (Searle, 1980), we twist its original intent by enabling humans to translate text, e.g. from Uyghur to English, even if they don’t have any prior knowledge of the source language. Our enabling tool, which we call the Chinese Room, is equipped with the same resources made available to a machine translation engine. We find that our superior language model and world knowledge allows us to create perfectly fluent and nearly adequate translations, with human expertise required only for the target language. The Chinese Room tool can be used to rapidly create small corpora of parallel data when bilingual translators are not readily available, in particular for low-resource languages.
Anthology ID:
P18-4011
Volume:
Proceedings of ACL 2018, System Demonstrations
Month:
July
Year:
2018
Address:
Melbourne, Australia
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
62–67
Language:
URL:
https://aclanthology.org/P18-4011
DOI:
10.18653/v1/P18-4011
Bibkey:
Cite (ACL):
Ulf Hermjakob, Jonathan May, Michael Pust, and Kevin Knight. 2018. Translating a Language You Don’t Know In the Chinese Room. In Proceedings of ACL 2018, System Demonstrations, pages 62–67, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Translating a Language You Don’t Know In the Chinese Room (Hermjakob et al., ACL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/P18-4011.pdf