Phrase Quality Performance Score (QPS)
Phrase QPS is an AI Quality Estimation system intended to predict scores derived from the industry-standard Multidimensional Quality Metrics (MQM) framework. It takes both source text in the original language and the translated target text (from MT or otherwise) and provides in response a score ranging from 0 to 100 reflecting what it believes the translation would score were it reviewed by a human using the MQM evaluation framework.
Phrase QPS is available for all editions of Phrase TMS , Phrase Language AI via API, and Phrase Strings.
Phrase TMS implementation
-
Phrase QPS replaces MT Quality Estimation in all places where this feature was previously available.
-
QPS scores appear at the segment level together with other translation resources (TM, NT, TB). Match origin is presented in a tooltip and at the bottom of the CAT panel in the metadata section.
-
If enabled, QPS scoring is displayed in the Phrase Portal translation interface to evaluate the MT quality of file translations.
-
A dedicated dashboard in Phrase Analytics helps find the optimal QPS threshold to balance cost savings and quality risks.
-
Phrase QPS requires a Phrase Language AI subscription.
-
Previously MTQE scores were only available in four categories: 0, 75, 99, 100. Phrase QPS uses integer values ranging from 0 to 100.
Note
Due to continuous improvements, the user interface may not be exactly the same as presented in the video.
Phrase Language AI via API
-
Users will have access to document-level scores via the API, which will enable them to quickly identify the quality of a translated document.
Phrase Strings Implementation
-
QPS scores are added to the editor.
-
When a translation is saved, Strings automatically assigns a score of 0-100.
-
Scores will help translators identify where to target their attention for higher-quality output.
-
Users will be able to toggle on and off the option to display QPS scores in the editor.
Note
Due to continuous improvements, the user interface may not be exactly the same as presented in the video.
Phrase Orchestrator Implementation
-
QPS endpoint is available as an action to create workflows that automatically route content based on QPS scores:
-
Users can create TMS workflows and define which segments should be sent for human review based on specified QPS score.
-
Users can create TMS workflows and define which group of segments should be sent for LQA based on specified QPS score.
-
Users can create Strings workflows to evaluate keys for quality, which can then be routed according to user-defined decision criteria.
-
Note
Due to continuous improvements, the user interface may not be exactly the same as presented in the video.
Scoring categories:
-
95 - 100: Excellent
The highest level of translation quality. Excellent translations are fluent, accurate and stylistically appropriate.
-
90 -94: Very good
A high-quality translation with limited room for improvement. Very good translations capture the content of the source and articulate it well in target.
-
75 - 89: Good
A good translation of source content, with room to improve the fluency and stylistic expression of the target text.
-
0 - 74: Poor
A poor translation may fail to communicate source content with sufficient accuracy and clarity.
Codes are based on ISO 639-1.
|
Source |
Target |
|---|---|
|
ar |
en |
|
ca |
es |
|
cs |
bg |
|
cs |
de |
|
cs |
en |
|
cs |
es |
|
cs |
fr |
|
cs |
hu |
|
cs |
it |
|
cs |
pl |
|
cs |
ro |
|
cs |
ru |
|
cs |
sk |
|
cs |
sl |
|
cs |
sv |
|
cs |
uk |
|
cy |
en |
|
da |
de |
|
da |
en |
|
da |
es |
|
da |
fi |
|
da |
fr |
|
da |
nb |
|
da |
nl |
|
da |
pl |
|
da |
sv |
|
de |
cs |
|
de |
da |
|
de |
en |
|
de |
es |
|
de |
fi |
|
de |
fr |
|
de |
it |
|
de |
lv |
|
de |
nb |
|
de |
nl |
|
de |
pl |
|
de |
ro |
|
de |
ru |
|
de |
sk |
|
de |
sl |
|
de |
sr |
|
de |
sv |
|
el |
en |
|
en |
af |
|
en |
ar |
|
en |
as |
|
en |
az |
|
en |
bg |
|
en |
bn |
|
en |
bs |
|
en |
ca |
|
en |
cs |
|
en |
cy |
|
en |
da |
|
en |
de |
|
en |
el |
|
en |
es |
|
en |
et |
|
en |
fa |
|
en |
fi |
|
en |
fil |
|
en |
fr |
|
en |
ga |
|
en |
gu |
|
en |
he |
|
en |
hi |
|
en |
hr |
|
en |
hu |
|
en |
hy |
|
en |
id |
|
en |
is |
|
en |
it |
|
en |
ja |
|
en |
kk |
|
en |
kn |
|
en |
ko |
|
en |
lt |
|
en |
lv |
|
en |
mi |
|
en |
ml |
|
en |
mr |
|
en |
ms |
|
en |
mt |
|
en |
nb |
|
en |
ne |
|
en |
nl |
|
en |
or |
|
en |
pa |
|
en |
pl |
|
en |
pt |
|
en |
ro |
|
en |
ru |
|
en |
sk |
|
en |
sl |
|
en |
sq |
|
en |
sr |
|
en |
sv |
|
en |
ta |
|
en |
te |
|
en |
th |
|
en |
tl |
|
en |
tr |
|
en |
uk |
|
en |
ur |
|
en |
vi |
|
en |
zh-hans |
|
en |
zh-hant |
|
es |
cs |
|
es |
de |
|
es |
en |
|
es |
fr |
|
es |
it |
|
es |
nl |
|
es |
pt |
|
es |
ru |
|
et |
en |
|
et |
fi |
|
et |
lt |
|
et |
lv |
|
et |
ru |
|
fi |
de |
|
fi |
en |
|
fi |
et |
|
fi |
ru |
|
fi |
sv |
|
fr |
cs |
|
fr |
de |
|
fr |
en |
|
fr |
es |
|
fr |
id |
|
fr |
it |
|
fr |
nl |
|
fr |
pt |
|
fr |
ru |
|
hr |
de |
|
hr |
en |
|
id |
en |
|
it |
cs |
|
it |
de |
|
it |
en |
|
it |
es |
|
it |
fr |
|
it |
pl |
|
it |
pt |
|
it |
ru |
|
ja |
en |
|
ja |
es |
|
ja |
fr |
|
ja |
id |
|
ja |
ko |
|
ja |
ru |
|
ja |
zh-hans |
|
ja |
zh-hant |
|
ko |
en |
|
ko |
ja |
|
lt |
en |
|
lt |
et |
|
lt |
lv |
|
lt |
pl |
|
lt |
ru |
|
lv |
en |
|
lv |
et |
|
lv |
ru |
|
nb |
da |
|
nb |
de |
|
nb |
en |
|
nb |
fi |
|
nb |
nn |
|
nb |
sv |
|
nl |
de |
|
nl |
en |
|
nl |
fr |
|
pl |
cs |
|
pl |
de |
|
pl |
en |
|
pl |
it |
|
pl |
lt |
|
pl |
nl |
|
pl |
ro |
|
pl |
ru |
|
pl |
sk |
|
pt |
en |
|
pt |
es |
|
pt |
fr |
|
pt |
it |
|
ro |
en |
|
ru |
cs |
|
ru |
el |
|
ru |
en |
|
ru |
es |
|
ru |
et |
|
ru |
fr |
|
ru |
ky |
|
ru |
lt |
|
ru |
lv |
|
ru |
pt |
|
sk |
cs |
|
sk |
de |
|
sk |
en |
|
sk |
hu |
|
sl |
en |
|
sr |
en |
|
sv |
ar |
|
sv |
da |
|
sv |
de |
|
sv |
en |
|
sv |
es |
|
sv |
et |
|
sv |
fa |
|
sv |
fi |
|
sv |
fr |
|
sv |
is |
|
sv |
it |
|
sv |
nb |
|
sv |
nl |
|
sv |
pl |
|
sv |
ru |
|
th |
en |
|
tr |
ar |
|
tr |
en |
|
uk |
en |
|
vi |
en |
|
zh-hans |
en |
|
zh-hans |
ja |
|
zh-hant |
en |