23 votes

What is the actual quality of machine translations?

Who claimed that machine translation is as good as a human translator? For me, as a professional translator who makes his living on translation for 35 years now, MT means that my daily production of ...
  • 231
7 votes

What is the actual quality of machine translations?

Google's translations can be useful, especially if you know that the translations are not perfect and if you just want to have an initial idea of the meaning of the text (whose Google's translations ...
  • 35k
6 votes

What is the actual quality of machine translations?

You have asked quite a lot of questions, some of which cannot be answered definitively . To give an insight of the quality (and its history) of machine translations I like to refer to Christopher ...
  • 161
5 votes
Accepted

Why does Google Translate produce two different translations for the same Chinese text?

It's not quite clear what you are asking. So I'll answer in separate parts. Why is the translation different from the official title? It could be simply because machine translation is not perfect, ...
4 votes

How is Google Translate able to convert texts of different lengths?

Usually, in natural language processing (NLP), they are using Sequence to Sequence Learning (Seq2Seq) with Neural Networks, such as Recurrent Neural Networks or more recently the Transformer (you can ...
  • 1,098
4 votes

What is the actual quality of machine translations?

It really depends on the language pair and the topic of the content. Translating to/from English to any other language usually is the best supported. Translating to and from popular languages works ...
3 votes

What are the main differences between a language model and a machine translation model?

The simple language model will give you the probability of a sequence of tokens(sentence) for that language. So lets say if you have trained a model for English language your model can give you the ...
3 votes
Accepted

Why can't we use Google Translate for every translation task?

Google has achieved significant progress in AI translation, but it's still no-where near a qualified human translator. Natural language translation is already very challenging, adding domain knowledge ...
  • 1,390
2 votes
Accepted

Do I need an encoder-decoder architecture to predict the next item of a sequence?

You don't need to Encoder-Decoder here. When using seq2seq learning for text (for example, for translation) you need encoder-decoder to encode the words into the numeric vectors and decode the vectors ...
  • 1,683
2 votes

What is the actual quality of machine translations?

Apologies for not writing in English. Please find the adapted translation here: To give interested people an idea of the quality of MT (DeepL) please see this example from a text I was working on ...
  • 21
2 votes

What is the actual quality of machine translations?

Am I wrong and Google's translations are nevertheless readable, helpful and useful for a majority of users? Yes, they are somewhat helpful and allow you to translate faster. Or does Google have ...
2 votes
Accepted

Is there any resource that describes in detail a naive example-based machine translation algorithm?

I have not found any simple implementation of a naive EBMT system, but I found some articles, papers and books that may be helpful (although I haven't read them, apart from the first and last one), so ...
  • 35k
2 votes

How to do machine translation with no labeled data?

In this paper: Unsupervised Machine Translation Using Monolingual Corpora Only the authors proposed a novel method. Intuitively it is an autoencoder, but the Start Of Sentence token is set to be ...
2 votes

How is Google Translate able to translate texts of arbitrarily large length?

You simply split the sequence into smaller sequences; while there are some long-distance dependencies in language, that is generally not a problem for this. A sentence would typically be short enough, ...
  • 5,167
2 votes

Why does Google Translate produce two different translations for the same Chinese text?

As you know google translation works base on statistical methods. In statistical translation, many parameters can be related to the final result. One of these parameters is co-occurrence of words in a ...
  • 1,683
1 vote

BERT2: How to use GPT2LMHeadModel to start a sentence, not complete it

Based on our conversation in the comment section, what Mucida wants is a reformulation of the input, e.g. if the input is: "A company director has a pecuniary duty" the output should be: A ...
1 vote
Accepted

Given the immaturity of NLP tools for non-English languages, should I first translate the non-English language to English before text pre-processing?

Check SpaCy, it's a powerful NLP library that provides lot of different language models, including one for Portuguese. To answer the more generic question, translating to another language undermines ...
1 vote

Does it make sense to use BLEU or ROUGE for any machine translation task?

Yes - and no. The important distinction is whether your data contains proper word boundaries and rigorous translation references. BLEU and ROGUE both work by comparing a candidate (ie, model output) ...
  • 1,266
1 vote

What is the purpose of "alignment" in the self-attention mechanism of transformers?

Alignment: We all know that a good translation cannot be done just by splitting words, converting them, and concatenating them back. Otherwise, a dictionary would be just enough. One translation ...
1 vote

Can we use NLP to understand/parse/compile programming code?

Yes, and that is the ambition of the Decoder project (H2020 funded in Europe). Analyzing with NLP techniques the comments in e.g. C or C++ source code (of open source projects, and perhaps their ...
1 vote
Accepted

What happens when the output length in the brevity penalty is zero?

Division by zero is not mathematically defined. A usual or standard way of dealing with this issue is to raise an exception. For example, in Python, the exception ...
  • 35k
1 vote

What is the actual quality of machine translations?

Surprisingly all the other answers are very vague and try to approach this from the human translator POV. Let's switch over to ML engineer. When creating a translation tool, one of the first ...
1 vote

What is the actual quality of machine translations?

This will be not so much an answer as a commentary. The quality depends on several things, including (as Aaron said above) 1) the language pair and 2) the topic, but also 3) the genera and 4) the ...
1 vote

How do I identify a monologue or dialogue in a conversation?

There are a few different ways you could frame the problem... For example, the simplest, yet probably not the most effective, would be to treat it as a supervised classification task. In this case, ...
1 vote

Do I need an encoder-decoder architecture to predict the next item of a sequence?

Why you need encoder and decoder here, this is not a use case for this. If you want to convert one sequence to another sequence then you can use encoder-decoder. You can use simple seq2seq learning ...
1 vote

Why can't we use Google Translate for every translation task?

This is an good question and I have to wonder if someday we might. It may simply be a matter of formalizing all of the concepts conveyed by humans, which is emergent, but has to be finite. The ...
  • 6,107
1 vote

Why does Google Translate produce two different translations for the same Chinese text?

Google uses user input to improve translation. Some user may have provided an input to the Traditional Chinese characters using English characters only instead of pinyin, which would introduce a ...
1 vote

Why does Google Translate produce two different translations for the same Chinese text?

Chinese words 'fu' means with different intonation marks either happiness, huspand or tiger. Without correct intonation notation in English it may translate in Chinese as Tiger. Movie title has ...
  • 927

Only top scored, non community-wiki answers of a minimum length are eligible