0
Translating Akkadian to English with neural machine translation
Gai Gutherz, Shai Gordin, Luis Sáenz et al., 2023.
What it's used for here
PNAS Nexus 2(5), pgad096. Neural machine translation of Akkadian from transliteration (T2E) and from Unicode cuneiform (C2E) into English, trained on 56,160 sentences from five ORACC corpora (RINAP, RIAo, RIBo, SAAo, Suhu; 8,056 tablets, mostly Neo-Assyrian). BLEU4 37.47 (T2E) and 36.52 (C2E) against a translation-memory baseline of 23.51 and 27.09; best on sentences under about 118 characters; hallucinations noted. Used for the state of machine translation of Akkadian and its limits.
Cited by on this site 7 records
FIG
The unread cuneiform: half a million tablets and the limits of Sumerian
MYSThe mystery article
Cite it
Gai Gutherz, Shai Gordin, Luis Sáenz, Omer Levy, & Jonathan Berant (2023). Translating Akkadian to English with neural machine translation. https://doi.org/10.1093/pnasnexus/pgad096
@article{gutherz2023akkadian,
author = {Gai Gutherz} and {Shai Gordin} and {Luis Sáenz} and {Omer Levy} and {Jonathan Berant},
title = {Translating Akkadian to English with neural machine translation},
year = {2023},
doi = {10.1093/pnasnexus/pgad096},
url = {https://doi.org/10.1093/pnasnexus/pgad096}
}TY - JOUR TI - Translating Akkadian to English with neural machine translation AU - Gai Gutherz AU - Shai Gordin AU - Luis Sáenz AU - Omer Levy AU - Jonathan Berant PY - 2023 DO - 10.1093/pnasnexus/pgad096 UR - https://doi.org/10.1093/pnasnexus/pgad096 ER -
et al.. “Translating Akkadian to English with neural machine translation.” 2023. https://doi.org/10.1093/pnasnexus/pgad096.