NLP // Create vector representation of words using 'count-based' model
So I know most people use prediction/regression models now like GloVe or word2vec, and creating vectors using the count-based model should actually be simpler, but I'm having a difficult time figuring it out (I think because I don't have much background in programming).
Basically, I want to create vector representations of English words, and I want to be able to set the dimensions for each vector (which will probably be something like the 2,000 most frequent words in whatever corpus I end up using). I also want to be able to set the window (for instance, look at x number of words before and after the target word).
What would be the best way to get started doing this (preferably using python)?
python vector nlp
asked Nov 26 '18 at 3:06
WillWill
245
add a comment |
So I know most people use prediction/regression models now like GloVe or word2vec, and creating vectors using the count-based model should actually be simpler, but I'm having a difficult time figuring it out (I think because I don't have much background in programming).
Basically, I want to create vector representations of English words, and I want to be able to set the dimensions for each vector (which will probably be something like the 2,000 most frequent words in whatever corpus I end up using). I also want to be able to set the window (for instance, look at x number of words before and after the target word).
What would be the best way to get started doing this (preferably using python)?
python vector nlp
asked Nov 26 '18 at 3:06
WillWill
245
1
scikit-learn.org/stable/tutorial/text_analytics/…
– min2bro
Nov 26 '18 at 3:40
Thanks. Maybe I'm too dense, but I can't figure out from this how I would set up the dimensions for the vectors or set up the window
– Will
Nov 26 '18 at 5:59
1
do you just want to create an array/vector of word counts? when you say 'each vector', what does each mean? What should a vector represent for you?
– AbtPst
Nov 28 '18 at 19:49
@AbtPst I want to download a corpus, find the 2,000 most frequent words (excluding stop words) and use those as the dimensions for the vector representations. Then I want to go through the same corpus, and select a window, say five words before each target word and five words after, and use the frequencies of how often each target word appears in the same window as a context word (one of the 2,000 most frequent). I want to use pointwise mutual info for weighting. So I want to end up with a txt file where each word is followed by 2,000 numbers, each representing one of those 2000
– Will
Nov 29 '18 at 0:49
Perhaps scikit-learn is the best way to do that, but I can't figure out how to set up a window or employ pointwise mutual infomation
– Will
Nov 29 '18 at 0:51
add a comment |
So I know most people use prediction/regression models now like GloVe or word2vec, and creating vectors using the count-based model should actually be simpler, but I'm having a difficult time figuring it out (I think because I don't have much background in programming).
Basically, I want to create vector representations of English words, and I want to be able to set the dimensions for each vector (which will probably be something like the 2,000 most frequent words in whatever corpus I end up using). I also want to be able to set the window (for instance, look at x number of words before and after the target word).
What would be the best way to get started doing this (preferably using python)?
python vector nlp
asked Nov 26 '18 at 3:06
WillWill
245
So I know most people use prediction/regression models now like GloVe or word2vec, and creating vectors using the count-based model should actually be simpler, but I'm having a difficult time figuring it out (I think because I don't have much background in programming).
Basically, I want to create vector representations of English words, and I want to be able to set the dimensions for each vector (which will probably be something like the 2,000 most frequent words in whatever corpus I end up using). I also want to be able to set the window (for instance, look at x number of words before and after the target word).
What would be the best way to get started doing this (preferably using python)?
python vector nlp
python vector nlp
asked Nov 26 '18 at 3:06
WillWill
245
asked Nov 26 '18 at 3:06
WillWill
245
asked Nov 26 '18 at 3:06
WillWill
245
asked Nov 26 '18 at 3:06
WillWill
245
asked Nov 26 '18 at 3:06
WillWill
245
245
1
scikit-learn.org/stable/tutorial/text_analytics/…
– min2bro
Nov 26 '18 at 3:40
Thanks. Maybe I'm too dense, but I can't figure out from this how I would set up the dimensions for the vectors or set up the window
– Will
Nov 26 '18 at 5:59
1
do you just want to create an array/vector of word counts? when you say 'each vector', what does each mean? What should a vector represent for you?
– AbtPst
Nov 28 '18 at 19:49
@AbtPst I want to download a corpus, find the 2,000 most frequent words (excluding stop words) and use those as the dimensions for the vector representations. Then I want to go through the same corpus, and select a window, say five words before each target word and five words after, and use the frequencies of how often each target word appears in the same window as a context word (one of the 2,000 most frequent). I want to use pointwise mutual info for weighting. So I want to end up with a txt file where each word is followed by 2,000 numbers, each representing one of those 2000
– Will
Nov 29 '18 at 0:49
Perhaps scikit-learn is the best way to do that, but I can't figure out how to set up a window or employ pointwise mutual infomation
– Will
Nov 29 '18 at 0:51
add a comment |
1
scikit-learn.org/stable/tutorial/text_analytics/…
– min2bro
Nov 26 '18 at 3:40
Thanks. Maybe I'm too dense, but I can't figure out from this how I would set up the dimensions for the vectors or set up the window
– Will
Nov 26 '18 at 5:59
1
do you just want to create an array/vector of word counts? when you say 'each vector', what does each mean? What should a vector represent for you?
– AbtPst
Nov 28 '18 at 19:49
@AbtPst I want to download a corpus, find the 2,000 most frequent words (excluding stop words) and use those as the dimensions for the vector representations. Then I want to go through the same corpus, and select a window, say five words before each target word and five words after, and use the frequencies of how often each target word appears in the same window as a context word (one of the 2,000 most frequent). I want to use pointwise mutual info for weighting. So I want to end up with a txt file where each word is followed by 2,000 numbers, each representing one of those 2000
– Will
Nov 29 '18 at 0:49
Perhaps scikit-learn is the best way to do that, but I can't figure out how to set up a window or employ pointwise mutual infomation
– Will
Nov 29 '18 at 0:51
1
1
scikit-learn.org/stable/tutorial/text_analytics/…
– min2bro
Nov 26 '18 at 3:40
scikit-learn.org/stable/tutorial/text_analytics/…
– min2bro
Nov 26 '18 at 3:40
Thanks. Maybe I'm too dense, but I can't figure out from this how I would set up the dimensions for the vectors or set up the window
– Will
Nov 26 '18 at 5:59
Thanks. Maybe I'm too dense, but I can't figure out from this how I would set up the dimensions for the vectors or set up the window
– Will
Nov 26 '18 at 5:59
1
1
do you just want to create an array/vector of word counts? when you say 'each vector', what does each mean? What should a vector represent for you?
– AbtPst
Nov 28 '18 at 19:49
do you just want to create an array/vector of word counts? when you say 'each vector', what does each mean? What should a vector represent for you?
– AbtPst
Nov 28 '18 at 19:49
@AbtPst I want to download a corpus, find the 2,000 most frequent words (excluding stop words) and use those as the dimensions for the vector representations. Then I want to go through the same corpus, and select a window, say five words before each target word and five words after, and use the frequencies of how often each target word appears in the same window as a context word (one of the 2,000 most frequent). I want to use pointwise mutual info for weighting. So I want to end up with a txt file where each word is followed by 2,000 numbers, each representing one of those 2000
– Will
Nov 29 '18 at 0:49
@AbtPst I want to download a corpus, find the 2,000 most frequent words (excluding stop words) and use those as the dimensions for the vector representations. Then I want to go through the same corpus, and select a window, say five words before each target word and five words after, and use the frequencies of how often each target word appears in the same window as a context word (one of the 2,000 most frequent). I want to use pointwise mutual info for weighting. So I want to end up with a txt file where each word is followed by 2,000 numbers, each representing one of those 2000
– Will
Nov 29 '18 at 0:49
Perhaps scikit-learn is the best way to do that, but I can't figure out how to set up a window or employ pointwise mutual infomation
– Will
Nov 29 '18 at 0:51
Perhaps scikit-learn is the best way to do that, but I can't figure out how to set up a window or employ pointwise mutual infomation
– Will
Nov 29 '18 at 0:51
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
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: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
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%2fstackoverflow.com%2fquestions%2f53474295%2fnlp-create-vector-representation-of-words-using-count-based-model%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
Thanks for contributing an answer to Stack Overflow!
- 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.
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%2fstackoverflow.com%2fquestions%2f53474295%2fnlp-create-vector-representation-of-words-using-count-based-model%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
1
scikit-learn.org/stable/tutorial/text_analytics/…
– min2bro
Nov 26 '18 at 3:40
Thanks. Maybe I'm too dense, but I can't figure out from this how I would set up the dimensions for the vectors or set up the window
– Will
Nov 26 '18 at 5:59
1
do you just want to create an array/vector of word counts? when you say 'each vector', what does each mean? What should a vector represent for you?
– AbtPst
Nov 28 '18 at 19:49
@AbtPst I want to download a corpus, find the 2,000 most frequent words (excluding stop words) and use those as the dimensions for the vector representations. Then I want to go through the same corpus, and select a window, say five words before each target word and five words after, and use the frequencies of how often each target word appears in the same window as a context word (one of the 2,000 most frequent). I want to use pointwise mutual info for weighting. So I want to end up with a txt file where each word is followed by 2,000 numbers, each representing one of those 2000
– Will
Nov 29 '18 at 0:49
Perhaps scikit-learn is the best way to do that, but I can't figure out how to set up a window or employ pointwise mutual infomation
– Will
Nov 29 '18 at 0:51