Skip to main content

Questions tagged [machine-translation]

Issues related to translation of text or speech as done by computer programs. Can refer to the software, models, methodology, algorithms, performance, and theory of MT (machine translation), including issues in pre- and post-processing.

Filter by
Sorted by
Tagged with
1 vote
1 answer
55 views

Is there any theory for mathematically judging the quality of a parallel corpus before running it through a machine translation pipeline?

The performance of a machine translation system is highly impacted by the parallel corpus it is trained on. Therefore, as we all know, a good quality normalized and (ideally) noise-free corpus is ...
0 votes
1 answer
184 views

Translating unknown language with AI

I've read around the web there are AI's they used to translate ancient languages, even without any comparation with known texts. What I wasn't unable to find, is the specifications of those AIs, and ...
3 votes
2 answers
558 views

How good is a round-trip translation as a machine translation quality evaluation technique?

I recently had a text translated into Icelandic. When I machine translate that human translation back to English, it came out as quite awkward English. However, when I machine translate the machine ...
1 vote
3 answers
179 views

Computer generated/aided glossing

I want to experiment with innovative ways of presenting a written text on a printed page to help a non-native speaker to read it. The example I have in mind is the Iliad for people whose native ...
4 votes
1 answer
217 views

Accuracy of automatic (machine) translation of two languages in same language family

Are there any statistic on how accuracy the automated (program/machine) transition from one language to another language of the same language family? For example from turkey to azerbaijan, uzbek, ...
3 votes
1 answer
1k views

What are the best NLP sentence alignment tools?

Which tools are worthwhile for aligning sentences from pairs of paragraphs of source and target languages.
0 votes
3 answers
251 views

Some “linguistic formulas” to translate French texts into English?

I am not sure is it correct to ask my question here or not! I've asked this question here (in MathStackExchange) before! Maybe it is better to see the question there, because it was written ...
4 votes
1 answer
178 views

How to localize country names in phrases?

I want to localize phrases like "Places in {country name}" where the (already localized) country name is dynamically obtained according to the ISO country code. The problem is that for some ...
0 votes
3 answers
468 views

Can I simply check the unicode or UTF-8 mapping of character to infer the language?

I am given a language detection problem. I was wondering if it could be solved just by looking at the encoding map of characters used and decide which language it is. Is there too much overlap of ...
3 votes
3 answers
13k views

Is there an English to Coptic translator online?

I've found two sites that claim to do this, neither of them work. I need a translator, not a dictionary. Non-workers: Bablefish Online Translator and a lot of spam... I wasn't sure whether this ...
5 votes
2 answers
11k views

Norwegian Translation Codes (no, nn, nb) - Which to use on a website?

I have a website which currently uses the Norwegian language code 'no' for translations, but I am not a native speaker and noticed some differences between 'no' and 'nb' when it comes to currency. Did ...
4 votes
1 answer
322 views

Is www.babelfish.com/success/ a rule-based engine?

Can anybody tell me if BabelFish translator is rule-based? I'd like to stress that "Babelfish translator" and "Yahoo!Babelfish" are not the same thing. In fact: "Yahoo!...
1 vote
1 answer
121 views

Seq2seq translation model. ValueError: An operation has `None` for gradient

So I'm trying to build a seq2seq encoder-decoder network for a translation task. I've been stuck now for a while, I have no idea how to fix the error I'm getting and would appreciate any help. My code ...
30 votes
3 answers
7k views

Why don't you get back the original text when you use translation software to translate something into another language and then back into English?

I translated "How to use Web?" into some other language using machine translation, but after I translated the result back into English, it is not the same as the first text I put into the translator. ...
1 vote
1 answer
78 views

What branch in computational linguistics should I study if I am interested in machine translation?

I am graduate student and I am doing a Master of Translation and interpretation Arabic English. I need to pursue study in machine translation but I do not know where exactly to start, NLP, ...
4 votes
1 answer
195 views

Can word embeddings between any two languages be transformed in a linear way?

In this paper: Word Translation Without Parallel Data researchers from FaceBook found that using a matrix and adversarial training the word embedding in one language can be transformed into(or ...
3 votes
0 answers
75 views

Computational linguist's estimate of minimum hours of speech needed to train a neural net to recognize speech

From a computational linguist's point of view, is there a lower limit on the number of hours of speech needed to train a neural net to translate speech to text? An estimate from CMU is 3000-5000 hours ...
3 votes
4 answers
604 views

Why does google translate produce awkward sentences

Anyone who has ever used Google translate knows that the translated version is mostly grammatically correct but often extremely awkward to use in a conversation. This is one of the factor which has ...
13 votes
3 answers
347 views

How do purely statistical machine translators deal with different word orders?

Even relatively closely related languages can differ greatly in word order. Take English and German for instance. English is pretty boringly subject-verb-object whereas in German the finite verb must ...
1 vote
0 answers
66 views

How to Create A Termbase without Creating Project in MemoQ?

Well, there was no platform on StackExchange for translation or translators, so I thought asking here is okay. As in title, is there a way to create a termbase and adding to it without creating a ...
0 votes
1 answer
80 views

Which original language would cause "your" to be translated to "their" in English? [closed]

We get a significant number of emails from people who seemingly use "their" in place of "your", which leads us to believe that the mails are machine translated. Does anyone know which language would ...
0 votes
1 answer
611 views

Bing Translate isn't same as the previous translation [duplicate]

When I translate "How to use something" in Bing Translate to Chinese, it shows "如何使用某物", but if I translate back, it will show "How to use a thing". What's the hell? When I'am translating other ...
1 vote
0 answers
77 views

Are there any statistic how similar are any two languages? [duplicate]

Are there any statistics on how similar any two languages are? For a whole language (lexical and structural) or maybe just a comparison of two dictionaries (vocabulary)?
2 votes
1 answer
176 views

Noisy channel model explanation

In the noisy channel model, for a given input sentence D we are given a set of possible translations A1, A2, A3, .., Ai, ... We want to pick the best possible translation, hence argmax(P(Ai|D)). When ...
3 votes
1 answer
1k views

Are European Union parallel multilingual texts ideal for machine learning of machine translation?

Are European Union parallel multilingual texts - regulations, directives, especially the debates of European parliament - ideal for machine learning of machine translation, e.g. with neural networks? ...
4 votes
1 answer
371 views

What is the best way to accurately translate slang?

It may not even be accurate to call it "slang"... I am working on a filtering system that blocks pornography. I have a set of key words and phrases in English. Essentially, I would like to have the ...
0 votes
1 answer
315 views

What are the various approaches to detect whether a sentence is complete or not?

I was working on creating a question answering system. Now I wanted to deal with incomplete or partial sentences. So the first step to this would be detecting whether the question entered by the user ...
4 votes
1 answer
116 views

What language pairs are underserved, and would most benefit from machine-learned bilingual tools?

What language pairs are under-served by current resources — like human translators, bilingual dictionaries, and parallel corpuses — relative to their linguistic importance, economic potential, or ...
0 votes
2 answers
323 views

Does machine learning still need a better linguistic theory?

Machine learning equipped with artificial intelligence is looking very promising in the field of machines understanding various human languages including English and translating one into another. I'm ...
2 votes
3 answers
186 views

To which extent language exists disconnected from the physical world?

If I would put you in a closed room with a computer containing terabytes of alien written symbols. Those aliens are from another dimension where the physical laws are different and our understanding ...
0 votes
1 answer
98 views

Enumerating the possible Pinyin -> Hanzi transcriptions

Pinyin Chinese text contains less information than its Hanzi equivalent, so its transcription is ambiguous: to identify the correct characters for some given Pinyin requires context. For this reason ...
5 votes
1 answer
576 views

Did Google Translate supply North Korea with the word "dotard" because of J.R.R. Tolkien's "Lord of the Rings"?

This question contains some speculation that a good answer would confirm or deny: The North Korean government recently released a statement that referred to Donald Trump, the current US president, as ...
0 votes
1 answer
192 views

Will machine translation eclipse the need for human translation some day and if so, by what date do you predict? [closed]

I recently listened to a TEDTalk given by Louis von Ahn, co-founder and CEO of Duolingo. During this talk, which he gave in 2011, he addresses the topic of machine translation a bit. Specificially, ...
0 votes
1 answer
831 views

How to get the similarity between languages?

Is there a good dataset or library or some trick for getting the similarity between languages, or n most similar languages? Similarity here means lexical and structural similarity for the purposes of ...
1 vote
0 answers
28 views

Reference text database for medical translation?

I'm working on machine translation for physicians, and I was wondering if there was a resource for medical reference texts? Where it shows an original English transcript, and then several possible "...
4 votes
2 answers
183 views

Network of Phonological Relationships

Does there exist a definitive network or database that maps the relationships between phonetic symbols? Similar to a word net, it would be a map representing the distance (or similarity) between ...
2 votes
0 answers
850 views

Is there a Python lib to calculate HTER?

Is there a Python lib that calculates HTER - Human-targeted Translation Error Rate? Ideally it would expose a function that takes as parameters 1) at least one golden translation and 2) the ...
3 votes
4 answers
349 views

"Episode 78" machine mistranslation etymology

This post on Rocket News 24 described a Google Translate bug, in which さよなら大好きな人 was translated into "Episode 78". This bug is still live as of the time of writing, and you can replicate it ...
2 votes
1 answer
383 views

Question about Range of BLEU

I read that range of BLEU is 0 to 1.(from "BLEU" page on wikipedia) But i found some paper says like "we achieve a significant gain of 5.0 BLEU points over non-attentional systems that already ...
2 votes
1 answer
64 views

How lexical ambiguity addressed in phrase-based SMT

I am wondering how the lexical ambiguity is addressed in phrase-based statistical machine translation?
3 votes
1 answer
834 views

What is being translated as "hello dear", and why? [closed]

It is fairly common on Stack Overflow for users to translate questions and/or responses into English using Google Translate. One of the more amusing patterns I've noticed is when a translated ...
4 votes
1 answer
141 views

Automated methods to align text

I have an assignment for my machine translation class which involves using the different language versions of websites as parallel corpora. The problem is the text isn't properly aligned. For example:...
4 votes
2 answers
429 views

Probabilities for 2-grams are higher than 1-grams in arpa file produced by kenlm

I'm using the 1 billion word language corpus to build a model with 1 and 2-grams. When using the lmplz program that comes with kenlm, I noticed that the arpa file seems to have higher probabilities ...
4 votes
6 answers
5k views

Which is the hardest language for a software translator to translate into English? [closed]

Many people i see over online auction sites and such use software translators for their benefit, but sometimes the outcome can be somewhat curious. Are these inaccuracies caused by the use of informal ...
3 votes
1 answer
220 views

Dictionaries for machine translation

I am doing research on machine translation in prolog and I am wondering if there are any suitable dictionaries available in text/xml format for machine translation. With suitable for machine ...
2 votes
0 answers
58 views

Generalisations which a bi-gram probabilistic model might infer from a dataset

I have the following exam question for a machine translation course: From my understanding, I assume the answer is looking for incorrect English grammar which get discovered by bi-grams. So the ...
2 votes
1 answer
432 views

Why do we need machine translation evaluation?

Why is it that we need machine translation evaluation? If we have subjective evaluation measures why do we need automatic evaluation? As most of the automatic evaluation metrics are unable to capture ...
3 votes
1 answer
124 views

Recommended Translation Textbooks/Resources

Please delete this if it's not appropriate for this Stack. I'm researching machine translation, and trying to read around the subject and understand better how human translators go about translating ...
8 votes
4 answers
2k views

Machine translation - Rule-Based and Statistics-Based approaches

My question is about the current situation in machine translation. I am aware about two main approaches to machine translation. One which is based in a strong way on linguistic theory and another ...
12 votes
2 answers
707 views

Bar-Hillel's critique of machine translation 50 years later

More than fifty years ago, philosopher Yehoshua Bar-Hillel wrote wrote an influential paper about computerized translation entitled: A Demonstration of the Nonfeasibility of Fully Automatic High ...