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
7
votes
1 answer

Word-level Seq2Seq with Keras

I was following the Keras Seq2Seq tutorial, and wit works fine. However, this is a character-level model, and I would like to adopt it to a word-level model. The authors even include a paragraph with require changes but all my current attempts…
Christian
  • 3,239
  • 5
  • 38
  • 79
7
votes
2 answers

Japanese Numerals to Arabic Numerals converter in Python

Is there an open source library in Python which does Kanji Numeral to Arabic Numeral conversion/translation? Input : 10億2千9百万 Output: 1,029,000,000 Input : 1億6,717万2,600 Output: 167,172,600 Input : 3,139百万 Output: 3,139,000,000 Japanese Numeral…
abhi488
  • 81
  • 5
6
votes
0 answers

How are SHAP's feature contributions calculated for models with word embeddings as output?

In a typical Shapley value estimation for a numerical regression task, there is a clear way in which the marginal contribution of an input feature i to the final numerical output variable can be calculated. For input features (age=45, location=’NY’,…
Daniel Gallagher
  • 84
  • 3
6
votes
2 answers

How to reduce the inference time of Helsinki-NLP/opus-mt-es-en (translation model) from transformer

Currently Helsinki-NLP/opus-mt-es-en model takes around 1.5sec for inference from transformer. How can that be reduced? Also when trying to convert it to onxx runtime getting this error: ValueError: Unrecognized configuration class
sambit9238
  • 281
  • 5
  • 8
6
votes
1 answer

What jobs does a typical C++ compiler handle?

After researching a bit on compilers and how they work I learned that the process is often broken up into 4 steps: Preprocessor, Compiler, Assembler and Linker. The way I envisioned these steps was each being it's own separate program; A…
Jason
  • 2,198
  • 3
  • 23
  • 59
6
votes
6 answers

Translator for website

I am develeping a website in 2 languages. one option is We can do own translation but that can take more development time. So i'm trying to find a plugin. I tried Microsoft Translator Widget and google translate gadget but both are not working for…
S B
  • 1,363
  • 12
  • 21
5
votes
2 answers

How do I translate using HuggingFace from Chinese to English?

I want to translate from Chinese to English using HuggingFace's transformers using a pretrained "xlm-mlm-xnli15-1024" model. This tutorial shows how to do it from English to German. I tried following the tutorial but it doesn't detail how to…
wtwtwt
  • 368
  • 4
  • 11
5
votes
2 answers

Add attention layer to Seq2Seq model

I have build a Seq2Seq model of encoder-decoder. I want to add an attention layer to it. I tried adding attention layer through this but it didn't help. Here is my initial code without attention # Encoder encoder_inputs =…
PeakyBlinder
  • 1,059
  • 1
  • 14
  • 35
5
votes
3 answers

Is it acceptable to have the same input multiple times in machine learning (with different output)?

I was wondering whether in machine learning it is acceptable to have a dataset that may contain the same input multiple times, but each time with another (valid!) output. For instance in the case of machine translation, an input sentence but each…
Bram Vanroy
  • 27,032
  • 24
  • 137
  • 239
5
votes
2 answers

Use the google transliterate api in python

I am trying to use google transliterate [1] to convert hindi words written in english to hindi. e.g- Input text- Main sahi hun. Required text -मैं सही हूँ I want to pass the input string to api and wants a required text in hindi language. I am…
Beginner
  • 721
  • 11
  • 27
5
votes
1 answer

Server-side software for translating languages?

I am searching for a server-side application (not a service, we need to host this ourselves) that can take a given string and translate it to another language. Open-source, paid, doesn't matter. Can anyone provide some recommendations?
tambler
  • 3,009
  • 2
  • 23
  • 26
5
votes
2 answers

What are some examples of Machine Translation applications/libraries currently being developed?

I'm interested in learning more about Machine Translation. While I have some very interesting books on the matter, I'd like to see some real world applications of MT's theories. I've found a couple open source projects just by searching…
Stephano
  • 5,716
  • 7
  • 41
  • 57
5
votes
3 answers

Translating parts of sentences based on its context

I am working on an application that needs to be able to translate parts of sentences. The problem is that if I send the parts to a translation API like Google Translate, the translations often don't make sense in the context they occurred in.…
Yaeger
  • 253
  • 4
  • 15
5
votes
1 answer

How to tune a Machine Translation model with huge language model?

Moses is a software to build machine translation models. And KenLM is the defacto language model software that moses uses. I have a textfile with 16GB of text and i use it to build a language model as such: bin/lmplz -o 5 text.arpa The…
alvas
  • 115,346
  • 109
  • 446
  • 738
5
votes
1 answer

Python: Goslate translation request returns "503: Service Unavailable"

A few months ago, I used Python's goslate package to translate a bunch of French text to English. When I tried to do so this morning, though, the service returned an error: import goslate gs = goslate.Goslate() print gs.translate('hello world',…
duhaime
  • 25,611
  • 17
  • 169
  • 224
1
2
3
…
23 24