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 ...
Herbert's user avatar
  • 231
8 votes
Accepted

Do full-text translators such as DeepL or Google Translate fall under the term "Generative AI"?

Generative AI, as defined by IBM research, refers to deep-learning models capable of creating new content, be it text, images, or other media, based on their training data. This definition indeed ...
FledDev's user avatar
  • 204
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 ...
nbro's user avatar
  • 40.5k
7 votes

Do full-text translators such as DeepL or Google Translate fall under the term "Generative AI"?

The distinction between "generative" and "non-generative" AI isn't an especially useful one. A language model (to first approximation) takes a sentence as input and tells you how ...
Ray's user avatar
  • 346
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 ...
RikH's user avatar
  • 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, ...
k.c. sayz 'k.c sayz''s user avatar
5 votes

Do full-text translators such as DeepL or Google Translate fall under the term "Generative AI"?

Actually it depends, generative models are specific kind of machine learning models. Generative often means a model that models the probability distribution of data $p(x)$, you cannot do translation ...
Dr. Snoopy's user avatar
  • 1,355
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 ...
Aaron Butacov's user avatar
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 ...
razvanc92's user avatar
  • 1,128
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 ...
Jayendra Parmar's user avatar
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 ...
SmallChess's user avatar
  • 1,411
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 ...
OmG's user avatar
  • 1,816
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 ...
Herbert's user avatar
  • 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 ...
user8426627's user avatar
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 ...
Lerner Zhang's user avatar
2 votes

How do Transformer decoders handle arbitrary length input?

At training time, the decoder uses a so-called triangular mask that prevents the self-attention to "look" at positions that are yet to be decoded. Because of that, nothing prevents the ...
Jindřich's user avatar
  • 391
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 ...
OmG's user avatar
  • 1,816
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, ...
Oliver Mason's user avatar
  • 5,387
2 votes

Machine Translation Transformers: Why Mask in Decoder?

Masking The purpose of masking in the decoder is to prevent the model from having access to future tokens when predicting the current token in the output sequence. During training, the model is given ...
Hans-Peter Schrei's user avatar
2 votes

Do full-text translators such as DeepL or Google Translate fall under the term "Generative AI"?

The original question has been updated so my answer is being updated to reflect this. The question being asked can be boiled down to just "What is it that makes something a generative AI?" I ...
Chthonic One's user avatar
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 ...
Andre Goulart's user avatar
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 ...
Raphael Lopez Kaufman's user avatar
1 vote

What are the differences between BLEU and METEOR?

Both BLEU and METEOR are meant to evaluate the overall translation quality. METEOR shows a slightly better correlation with human judgment than BLEU, however, it relies on n-gram alignment between the ...
Jindřich's user avatar
  • 391
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 ...
Edoardo Guerriero's user avatar
1 vote
Accepted

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) ...
Recessive's user avatar
  • 1,396
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 ...
Basile Starynkevitch's user avatar
1 vote
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 ...
nbro's user avatar
  • 40.5k
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 ...
nbro's user avatar
  • 40.5k
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 ...
MatthewRock's user avatar
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 ...
Mike Maxwell's user avatar

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