What is the best way to use word2vec for bilingual text similarity?2019 Community Moderator ElectionWhat is the best way to split a sentence for a keyword extraction task?Text-Classification-Problem: Is Word2Vec/NN the best approach?applying word2vec on small text filesHow word2vec understands the relationship between numbers?Best way to tokenize tweetBest practical algorithm for sentence similarityText understanding and mappingText Similarities: which nlp methods to use?What would be the best way to map similar ngramscan I use public pretrained word2vec, and continue train it for domain specific text?
Eliminate empty elements from a list with a specific pattern
Why do UK politicians seemingly ignore opinion polls on Brexit?
Is it wise to focus on putting odd beats on left when playing double bass drums?
Can a planet have a different gravitational pull depending on its location in orbit around its sun?
Is every set a filtered colimit of finite sets?
Where else does the Shulchan Aruch quote an authority by name?
Domain expired, GoDaddy holds it and is asking more money
Where to refill my bottle in India?
Is there a name of the flying bionic bird?
LWC and complex parameters
Email Account under attack (really) - anything I can do?
What does it exactly mean if a random variable follows a distribution
Is Social Media Science Fiction?
What do the Banks children have against barley water?
Crop image to path created in TikZ?
Why is my log file so massive? 22gb. I am running log backups
Unbreakable Formation vs. Cry of the Carnarium
Is it legal to have the "// (c) 2019 John Smith" header in all files when there are hundreds of contributors?
Ideas for 3rd eye abilities
Add an angle to a sphere
Is domain driven design an anti-SQL pattern?
How is it possible for user's password to be changed after storage was encrypted? (on OS X, Android)
What's the difference between repeating elections every few years and repeating a referendum after a few years?
Re-submission of rejected manuscript without informing co-authors
What is the best way to use word2vec for bilingual text similarity?
2019 Community Moderator ElectionWhat is the best way to split a sentence for a keyword extraction task?Text-Classification-Problem: Is Word2Vec/NN the best approach?applying word2vec on small text filesHow word2vec understands the relationship between numbers?Best way to tokenize tweetBest practical algorithm for sentence similarityText understanding and mappingText Similarities: which nlp methods to use?What would be the best way to map similar ngramscan I use public pretrained word2vec, and continue train it for domain specific text?
$begingroup$
I face a problem where I need to compute similarities over bilingual (English and French) texts. The "database" looks like this:
+-+-+-+
| |F|E|
+-+-+-+
|1|X|X|
+-+-+-+
|2| |X|
+-+-+-+
|3|X| |
+-+-+-+
|4|X| |
+-+-+-+
|5| |X|
+-+-+-+
|6|X|X|
+-+-+-+
|7|X| |
+-+-+-+
which means that I have English and French texts (variable long single sentences) for each "item" with either in both version (in this case the versions are loose translations of each other) or only in one language.
The task is to find the closest item ID for any incoming new sentence irrespective the actual language of either of the sentence in the "database" or of the incoming sentence (that is, the matching sentence in the "database" needn't necessarily be in the same language as the incoming sentence as long as the meaning is the closest). I hope this goal explanation is clear.
Originally I planned to build a word2vec from scratch for both languages (the vocabulary is quite specific so I would have preferred my own word2vec) and find similarities only for the corresponding language for each new sentence but this would omit all candidates from the items where the corresponding language sentences are missing.
So I wonder if generating a common word2vec encoding for the combined corpus is viable (the word2vec method itself being language agnostic) but I cannot figure out if such a solution would be superior.
Additionally, the number of the sentences is not very large (about 10.000) maybe word2vec generation from scratch is not the best idea on one hand, but there are really specific terms in the corpora on the other hand.
nlp text-mining word2vec
$endgroup$
add a comment |
$begingroup$
I face a problem where I need to compute similarities over bilingual (English and French) texts. The "database" looks like this:
+-+-+-+
| |F|E|
+-+-+-+
|1|X|X|
+-+-+-+
|2| |X|
+-+-+-+
|3|X| |
+-+-+-+
|4|X| |
+-+-+-+
|5| |X|
+-+-+-+
|6|X|X|
+-+-+-+
|7|X| |
+-+-+-+
which means that I have English and French texts (variable long single sentences) for each "item" with either in both version (in this case the versions are loose translations of each other) or only in one language.
The task is to find the closest item ID for any incoming new sentence irrespective the actual language of either of the sentence in the "database" or of the incoming sentence (that is, the matching sentence in the "database" needn't necessarily be in the same language as the incoming sentence as long as the meaning is the closest). I hope this goal explanation is clear.
Originally I planned to build a word2vec from scratch for both languages (the vocabulary is quite specific so I would have preferred my own word2vec) and find similarities only for the corresponding language for each new sentence but this would omit all candidates from the items where the corresponding language sentences are missing.
So I wonder if generating a common word2vec encoding for the combined corpus is viable (the word2vec method itself being language agnostic) but I cannot figure out if such a solution would be superior.
Additionally, the number of the sentences is not very large (about 10.000) maybe word2vec generation from scratch is not the best idea on one hand, but there are really specific terms in the corpora on the other hand.
nlp text-mining word2vec
$endgroup$
add a comment |
$begingroup$
I face a problem where I need to compute similarities over bilingual (English and French) texts. The "database" looks like this:
+-+-+-+
| |F|E|
+-+-+-+
|1|X|X|
+-+-+-+
|2| |X|
+-+-+-+
|3|X| |
+-+-+-+
|4|X| |
+-+-+-+
|5| |X|
+-+-+-+
|6|X|X|
+-+-+-+
|7|X| |
+-+-+-+
which means that I have English and French texts (variable long single sentences) for each "item" with either in both version (in this case the versions are loose translations of each other) or only in one language.
The task is to find the closest item ID for any incoming new sentence irrespective the actual language of either of the sentence in the "database" or of the incoming sentence (that is, the matching sentence in the "database" needn't necessarily be in the same language as the incoming sentence as long as the meaning is the closest). I hope this goal explanation is clear.
Originally I planned to build a word2vec from scratch for both languages (the vocabulary is quite specific so I would have preferred my own word2vec) and find similarities only for the corresponding language for each new sentence but this would omit all candidates from the items where the corresponding language sentences are missing.
So I wonder if generating a common word2vec encoding for the combined corpus is viable (the word2vec method itself being language agnostic) but I cannot figure out if such a solution would be superior.
Additionally, the number of the sentences is not very large (about 10.000) maybe word2vec generation from scratch is not the best idea on one hand, but there are really specific terms in the corpora on the other hand.
nlp text-mining word2vec
$endgroup$
I face a problem where I need to compute similarities over bilingual (English and French) texts. The "database" looks like this:
+-+-+-+
| |F|E|
+-+-+-+
|1|X|X|
+-+-+-+
|2| |X|
+-+-+-+
|3|X| |
+-+-+-+
|4|X| |
+-+-+-+
|5| |X|
+-+-+-+
|6|X|X|
+-+-+-+
|7|X| |
+-+-+-+
which means that I have English and French texts (variable long single sentences) for each "item" with either in both version (in this case the versions are loose translations of each other) or only in one language.
The task is to find the closest item ID for any incoming new sentence irrespective the actual language of either of the sentence in the "database" or of the incoming sentence (that is, the matching sentence in the "database" needn't necessarily be in the same language as the incoming sentence as long as the meaning is the closest). I hope this goal explanation is clear.
Originally I planned to build a word2vec from scratch for both languages (the vocabulary is quite specific so I would have preferred my own word2vec) and find similarities only for the corresponding language for each new sentence but this would omit all candidates from the items where the corresponding language sentences are missing.
So I wonder if generating a common word2vec encoding for the combined corpus is viable (the word2vec method itself being language agnostic) but I cannot figure out if such a solution would be superior.
Additionally, the number of the sentences is not very large (about 10.000) maybe word2vec generation from scratch is not the best idea on one hand, but there are really specific terms in the corpora on the other hand.
nlp text-mining word2vec
nlp text-mining word2vec
asked Nov 17 '18 at 13:26
HendrikHendrik
1,887132644
1,887132644
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
$begingroup$
This paper from Amazon explains how you can use aligned bilingual word embeddings to generate a similarity score between two sentences of different languages. Used movie subtitles in four language pairs (English to German, French, Portuguese and Spanish) to show the efficiency of their system.
"Unsupervised Quality Estimation Without Reference Corpus for Subtitle Machine Translation Using Word Embeddings"
New contributor
$endgroup$
add a comment |
Your Answer
StackExchange.ifUsing("editor", function ()
return StackExchange.using("mathjaxEditing", function ()
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix)
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
);
);
, "mathjax-editing");
StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "557"
;
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function()
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled)
StackExchange.using("snippets", function()
createEditor();
);
else
createEditor();
);
function createEditor()
StackExchange.prepareEditor(
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader:
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
,
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);
);
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f41353%2fwhat-is-the-best-way-to-use-word2vec-for-bilingual-text-similarity%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
$begingroup$
This paper from Amazon explains how you can use aligned bilingual word embeddings to generate a similarity score between two sentences of different languages. Used movie subtitles in four language pairs (English to German, French, Portuguese and Spanish) to show the efficiency of their system.
"Unsupervised Quality Estimation Without Reference Corpus for Subtitle Machine Translation Using Word Embeddings"
New contributor
$endgroup$
add a comment |
$begingroup$
This paper from Amazon explains how you can use aligned bilingual word embeddings to generate a similarity score between two sentences of different languages. Used movie subtitles in four language pairs (English to German, French, Portuguese and Spanish) to show the efficiency of their system.
"Unsupervised Quality Estimation Without Reference Corpus for Subtitle Machine Translation Using Word Embeddings"
New contributor
$endgroup$
add a comment |
$begingroup$
This paper from Amazon explains how you can use aligned bilingual word embeddings to generate a similarity score between two sentences of different languages. Used movie subtitles in four language pairs (English to German, French, Portuguese and Spanish) to show the efficiency of their system.
"Unsupervised Quality Estimation Without Reference Corpus for Subtitle Machine Translation Using Word Embeddings"
New contributor
$endgroup$
This paper from Amazon explains how you can use aligned bilingual word embeddings to generate a similarity score between two sentences of different languages. Used movie subtitles in four language pairs (English to German, French, Portuguese and Spanish) to show the efficiency of their system.
"Unsupervised Quality Estimation Without Reference Corpus for Subtitle Machine Translation Using Word Embeddings"
New contributor
New contributor
answered 15 hours ago
prabhakar267prabhakar267
1
1
New contributor
New contributor
add a comment |
add a comment |
Thanks for contributing an answer to Data Science Stack Exchange!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f41353%2fwhat-is-the-best-way-to-use-word2vec-for-bilingual-text-similarity%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown