The final integrated rule based pipeline is set up to translate from sumerian to english. The Phrase Based Machine Translation for Sumerian-English can be found here -
The Rule based engine is comprised of data from -
Further details regarding the project, setup, preprocessing and details regarding NMT vs Rule Based engine can be found in apertium-sux-eng repo as mentioned above.
The evaluation is done using the BLEU metric on the dev set as mentioned above -
| Machine Translation System | Mean | Median |
|---|---|---|
| rule based | 19.156 | 20.4517 |
| neural network | 18.868 | 6.881 |
The mean and median scores for both Rule Based and NMT Engine
with weightage of (0.75,0.25,0,0) over n-grams
| # | Objectives | Associated Deliverables |
|---|---|---|
| 1 | updateding transfer rules and SVO reordering, sumerian to english | the final compact updated Transfer rules with and post processing if required |
| 2 | Integrated pipeline and NMT Comparision | Developing a notebook interface to try out both Neural network and Rule based engine for (sentence or file), with comparison |