Week from 07/19 to 07/25

 This week we started to focus on the Machine Translation task. First I tried to understand how the "Tensorflow Neural Machine Translation" model is implemented. And then trained the model on QALD datasets.

How the datasets are created?

From the QALD datasets from QALD-3 to QALD-7, I created a dataset which consists of language pairs such as English-Spanish, English-Deutsch, etc. These pairs are created for all languages Deutsch, Spanish, French Brazilian Portuguese, Portuguese, Italian, Dutch, Hindi, Romanian, Persian, and Russian.

How the evaluation is done?

Using the "Tensorflow Neural Machine translation with attention model", trained the datasets created as said above and got the following results,

languageaccuracy %
spanish60.6299
german65.8595
french63.3587
russian14.6666
italian31.6301
portugese3.33333
pt_BR4.54545
hindi37.3333
dutch61.9422
persian8.14479
romanian52.3026

Observations

It is observed that the results are very poor. This can be due to reasons such as the small dataset size, small vocabulary.

Comments

Popular posts from this blog

DBpedia Neural Multilingual QA - GSoC project summery

Machine Translation Task

Week from 07/12 to 07/18