Stack Overflow
Stack Overflow

Questions tagged [machine-translation]

Machine Translation, a subfield of Natural Language Processing, is the automatic translation of human languages. While historical translators are based on Statistical Machine Translation, newer systems use Neural Networks which provide much better results.

Machine Translation is the automatic translation of human languages. Current examples include Google Translate, Yandex Translate, and Bing Translate, which all are based on Statistical Machine Translation. In the 1990s Babel Fish was the best known service - it used Rules-Based Translation.

In November 2016, Google also introduced a Machine Translation based on Neural Networks ((G)NMT). DeepL introduces a free Machine Translation Service in 2017 which provides measurably better results than Google Translate.

353 questions
0
votes
2 answers

Microsoft Custom Translator: File upload not working for SC tmx files

I am testing the new Microsoft Custom Translator and trying to train a system EN-SC, but the file upload fails. I am trying to upload unzipped TMX files, all less than 50 MB in size, as specified in the user's guide. The file names I have tried…
maria c laguardia
  • 15
  • 6
0
votes
0 answers

Microsoft translator API - notranslate option not working with Neural Network MT

Does anyone experience notranslate option is ignored when sending to Microsoft Neural Network MT? The same string works with SMT. I am sending this with "text/html". My example string:

For example, it is important to install the latest

yyamakaw
  • 11
  • 1
0
votes
1 answer

Tensorflow/nmt: How to get the encoder hidden states?

I have just started to work with tensorflow. I'm following the tutorial on neural machine translation given by Thang Luong, Eugene Brevdo, Rui Zhao here https://www.tensorflow.org/tutorials/seq2seq I want to use the model as an auto-encoder but I…
Peter Pan
  • 23
  • 6
0
votes
1 answer

IOError: [Errno 2] No such file or directory: when the name was made by looping over existing files

I'm trying to have the bottom part of the code iterate over some files. These files should be corresponding and are differentiated by a number, so the counter is to change the number part of the file. The file names are generated by looking through…
Helen
  • 3
  • 4
0
votes
1 answer

Not able to generate correct English to SQL translations using LSTM for machine translation

I'm using recurrent neural networks to train a model to translate sample english sentences such as "fetch all employee data" into sql such as "SELECT * FROM EMPLOYEE". Right now my program takes 100 epochs of training time but translates all the…
feanaro
  • 1
  • 3
0
votes
3 answers

Can I feed translations back to Google Cloud Translation API to train it?

I am using the Google Translate neural network (amazing improvement) via the Google Cloud Translation API in SDL Trados to process technical translations. Of course it needs heavy post-editing, mostly terminology and sometimes style. I would really…
Daniel Brvnišťan
  • 3
  • 2
0
votes
0 answers

Improving google translator api accuracy by using domain specific knowledge

Ive got some french text data (20000 lines) and corresponding english translation. This data is specific to insurance domain and hence will have some restrictions due to vocabulary. Now when Im using google to translate to do it, its giving me 90%…
vinita
  • 595
  • 1
  • 9
  • 24
0
votes
2 answers

Machine translation for multilingual sentiment analysis

I am trying to do sentiment analysis for non english languages like japenese, chinese, german etc. I want to know if any Machine translator available for translating documents in these languages to english. I am working on JAVA so I should be able…
Jagdeep
  • 1
0
votes
2 answers

Best evaluation method for real-time machine translation?

I'm aware that there are many different methods like BLEU, NIST, METEOR etc. They all have their pros and cons, and their effectiveness differs from corpus to corpus. I'm interested in real-time translation, so that two people could have a…
Nicholas Hassan
  • 949
  • 2
  • 10
  • 27
0
votes
1 answer

OpenNMT confusion use of `Optim.updateLearningRate`: `valid_loss` used as `ppl` arg

In train.py line 246, we have # update the learning rate optim.updateLearningRate(valid_loss, epoch) However, in onmt/Optim.py, inside function updateLearningRate() at line 37, we have: def updateLearningRate(self, ppl, epoch): ... …
Daniel
  • 1,428
  • 3
  • 16
  • 35
0
votes
1 answer

IBM Watson Language Translation - correct way to train using parallel corpus

I have a bunch of articles that are translated, which I want to use as training data for IBM Watson language translation. What is the correct way to use these articles for training? Do I use the whole article and its translation as an entry in the…
user2968505
  • 435
  • 2
  • 7
  • 18
0
votes
1 answer

How do I access the Watson Language Translator Service from Python on Bluemix?

I have a Python Flask app on my laptop that successfully accesses the Watson Language Translator on Bluemix precisely as described in the Bluemix API Documentation from watson_developer_cloud import LanguageTranslatorV2 as…
Lennart
  • 69
  • 6
0
votes
1 answer

Adding to vocab during Tensorflow seq2seq run

I am using the Tensorflow seq2seq tutorial to play with machine translation. Say I have trained the model for some time and determine that I want to supplement the original vocab with new words to enhance the quality of the model. Is there a way to…
jrthom18
  • 1
  • 3
0
votes
1 answer

How to differentiate between real improvement and random noise?

I am building an automatic translator in moses. To improve its performance, I use log-linear weight optimisation. This technique has a random component, which can affect slightly the final result (but I do not know exactly how much). Suppose that…
gergf
  • 118
  • 1
  • 8
0
votes
1 answer

Tensorflow seq2seq `feed_previous' argument`

I'm using the built-in tf.nn.seq2seq.embedding_attention_seq2seq() function and I have some problems with the feed_previous argument, during training, the groundtruth is fed into the decoder while during testing we feed the output of the last time…
Zhao
  • 2,043
  • 1
  • 17
  • 36
1 2 3
…
23 24