Difference between revisions of "Evalution kaz-tur Machine Translation System"
Purplemoon (talk | contribs) |
Purplemoon (talk | contribs) |
||
| Line 17: | Line 17: | ||
Besides calculating WER and PER for our Kazakh-Turkish MT system, we did the same for old apertium Kazakh-Turkish MT system. The procedure was the same for both of them. We took a small (1,025 tokens) Kazakh text, which was a concatenation of several articles from Wikipedia and translated it using the two MT systems. The output of each system was postedited independently to avoid biasing in favour of one particular system. |
Besides calculating WER and PER for our Kazakh-Turkish MT system, we did the same for old apertium Kazakh-Turkish MT system. The procedure was the same for both of them. We took a small (1,025 tokens) Kazakh text, which was a concatenation of several articles from Wikipedia and translated it using the two MT systems. The output of each system was postedited independently to avoid biasing in favour of one particular system. |
||
Then we calculated WER and PER for each using the apertium-eval-translator |
Then we calculated WER and PER for each using the apertium-eval-translator {http://wiki.apertium.org/wiki/apertium-eval-translator}. |
||
Revision as of 15:52, 17 September 2018
The system has been evaluated by measuring the translation quality, the error rate of text produced by the system when comparing with postedited versions of them.
The translation quality was measured using two metrics, the first was word error rate (WER), and the second was position-independent word error rate (PER). Both metrics are based on the Levenshtein distance (Levenshtein, 1965). Metrics based on word error rate were chosen as to be able to compare the system against systems based on similar technology, and to assess the usefulness of the system in a real setting, that is of translating for dissemination.
| System | WER(%) | PER(%) |
|---|---|---|
| new-system | 23.57 | 23.19 |
| old-system | 45.77 | 41.69 |
Besides calculating WER and PER for our Kazakh-Turkish MT system, we did the same for old apertium Kazakh-Turkish MT system. The procedure was the same for both of them. We took a small (1,025 tokens) Kazakh text, which was a concatenation of several articles from Wikipedia and translated it using the two MT systems. The output of each system was postedited independently to avoid biasing in favour of one particular system. Then we calculated WER and PER for each using the apertium-eval-translator {http://wiki.apertium.org/wiki/apertium-eval-translator}.
