Mdthbs

What is this spacecraft tethered to another spacecraft in LEO (vintage)

How did Mysterio have these drones?

Why force the nose of 737 Max down in the first place?

(2 of 11: Moon-or-Sun) What is Pyramid Cult's Favorite Camera?

Is it legal to use cash pulled from a credit card to pay the monthly payment on that credit card?

How could Nomadic scholars effectively memorize libraries worth of information

Is there a wealth gap in Boston where the median net worth of white households is $247,500 while the median net worth for black families was $8?

Does academia have a lazy work culture?

How to apply the changes to my `.zshrc` file after edit?

How much were the LMs maneuvered to their landing points?

What is the use of で in this sentence?

Why do planes need a roll motion?

Is a topological space considered to be a class in set theory?

How many oliphaunts died in all of the Lord of the Rings battles?

Does the Intel 8086 CPU have user mode and kernel mode?

Pointwise convergence of uniformly continuous functions to zero, but not uniformly

The Sword in the Stone

Finding minimum time for vehicle to reach to its destination

The best place for swimming in Arctic Ocean

Japanese reading of an integer

How did the Axis intend to hold the Caucasus?

How did the SysRq key get onto modern keyboards if it's rarely used?

Why is the number of local variables used in a Java bytecode method not the most economical?

Polyhedra, Polyhedron, Polytopes and Polygon

Which approach can I use to generate text based on multiple inputs?

AI that can generate programsWhat is the machine learning approach based on human learning?Can anyone suggest a small application based on an Artificial Intelligence which can be done by a beginner in AI?Can we combine multiple different neural networks in one?Approach to classify a photo and extract text from itLoading multiple trained models for use in multi-agent environmentWhat methods are there to generate artificial training examples based on existing training examples?Which libraries can be used for image caption generation?Generate QA dataset from large text corpusCan GANs be used to generate matching pairs to inputs?

.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty{ margin-bottom:0;
}

3

$begingroup$

I have a little experience in building various models, but I've never created anything like this, so just wondering if I can be pointed in the right direction.

I want to create (in python) a model which will generate text based on multiple inputs, varying from text input (vectorized) to timestamp and integer inputs.

For example, in the training data, the input might include:

eventType = ShotMade

shotType = 2

homeTeamScore = 2

awayTeamScore = 8

player = JR Smith

assist = George Hill

period = 1

and the output might be (possibly minus the hashtags):
JR Smith under the basket for 2! 8-4 CLE. #NBAonBTV #ThisIsWhyWePlay #PlayByPlayEveryDay #NBAFinals

or

JR Smith out here doing #WhateverItTakes to make Cavs fans forgive him. #NBAFinals

Where is the best place to look to get a good knowledge of how to do this?

neural-networks deep-learning python generative-model

share|improve this question

edited 8 hours ago

nbro

5,68844 gold badges1515 silver badges3232 bronze badges

asked 9 hours ago

HdotHdot

1622 bronze badges

New contributor

Hdot is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

add a comment | 

3

$begingroup$

I have a little experience in building various models, but I've never created anything like this, so just wondering if I can be pointed in the right direction.

I want to create (in python) a model which will generate text based on multiple inputs, varying from text input (vectorized) to timestamp and integer inputs.

For example, in the training data, the input might include:

eventType = ShotMade

shotType = 2

homeTeamScore = 2

awayTeamScore = 8

player = JR Smith

assist = George Hill

period = 1

and the output might be (possibly minus the hashtags):
JR Smith under the basket for 2! 8-4 CLE. #NBAonBTV #ThisIsWhyWePlay #PlayByPlayEveryDay #NBAFinals

or

JR Smith out here doing #WhateverItTakes to make Cavs fans forgive him. #NBAFinals

Where is the best place to look to get a good knowledge of how to do this?

neural-networks deep-learning python generative-model

share|improve this question

edited 8 hours ago

nbro

5,68844 gold badges1515 silver badges3232 bronze badges

asked 9 hours ago

HdotHdot

1622 bronze badges

New contributor

Hdot is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

add a comment | 

$begingroup$

I have a little experience in building various models, but I've never created anything like this, so just wondering if I can be pointed in the right direction.

I want to create (in python) a model which will generate text based on multiple inputs, varying from text input (vectorized) to timestamp and integer inputs.

For example, in the training data, the input might include:

eventType = ShotMade

shotType = 2

homeTeamScore = 2

awayTeamScore = 8

player = JR Smith

assist = George Hill

period = 1

and the output might be (possibly minus the hashtags):
JR Smith under the basket for 2! 8-4 CLE. #NBAonBTV #ThisIsWhyWePlay #PlayByPlayEveryDay #NBAFinals

or

JR Smith out here doing #WhateverItTakes to make Cavs fans forgive him. #NBAFinals

Where is the best place to look to get a good knowledge of how to do this?

neural-networks deep-learning python generative-model

share|improve this question

edited 8 hours ago

nbro

5,68844 gold badges1515 silver badges3232 bronze badges

asked 9 hours ago

HdotHdot

1622 bronze badges

New contributor

Hdot is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

share|improve this question

edited 8 hours ago

nbro

5,68844 gold badges1515 silver badges3232 bronze badges

asked 9 hours ago

HdotHdot

1622 bronze badges

New contributor

Hdot is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

share|improve this question

edited 8 hours ago

nbro

5,68844 gold badges1515 silver badges3232 bronze badges

asked 9 hours ago

HdotHdot

1622 bronze badges

New contributor

Hdot is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

edited 8 hours ago

nbro

5,68844 gold badges1515 silver badges3232 bronze badges

edited 8 hours ago

nbro

5,68844 gold badges1515 silver badges3232 bronze badges

asked 9 hours ago

HdotHdot

1622 bronze badges

New contributor

Hdot is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked 9 hours ago

HdotHdot

1622 bronze badges

1 Answer
1

active

oldest

votes

2

$begingroup$

Generally, text generators work by modeling the joint distribution of the text by its Bayesian forward decomposition

$
begin{align*}
p(w_1, w_2, ..., w_n) &= p(w_1) * p(w_2|w_1) * p(w_3|w_2, w_1) * ... * p(w_n|{w_i}_{i<n})\
&= prod_{i=1}^n p(w_i|{w_k}_{k<i})\
end{align*}
$

From a modeling perspective, this looks right up RNN's ally, where you can have a state holding information from ${w_k}_{k<i}$ to learn a representation of $w_i$

Now, in your specific case, you're interested in a conditional text-generator, so you are trying to model $p(w_1, w_2, ..., w_n | {v_j}_j)$, but this same tactic works.

$
begin{align*}
p(w_1, w_2, ..., w_n| {v_j}_j) &= p(w_1|{v_j}_j) * p(w_2|w_1, {v_j}_j) * p(w_3|w_2, w_1, {v_j}_j) * ... * p(w_n|{w_i}_{i<n}, {v_j}_j)\
&= prod_{i=1}^n p(w_i|{w_k}_{k<i}, {v_j}_j)\
end{align*}
$

So, in your RNN or forward-based model, you can use the exact same approach just additionally embed the conditional inputs you have and somehow infuse it into the model (in practice, I have seen this through attention, concatenation, or some other common approach).

My recommendation (depending on the computational power you have) is to take advantage of the recent fad of pre-trained language models. Specifically, ones trained on next word prediction will probably do the job best. A good example is gpt-2, and, if you check out their GitHub, their code is very readable and easy to adjust for adding conditional input in the ways I have described.

share|improve this answer

edited 6 hours ago

nbro

5,68844 gold badges1515 silver badges3232 bronze badges

answered 8 hours ago

mshlismshlis

93511 silver badge1414 bronze badges

$endgroup$

add a comment | 

Your Answer

StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "658"
};
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
},
noCode: true, onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});


}
});

Hdot is a new contributor. Be nice, and check out our Code of Conduct.

draft saved

draft discarded

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

Name

Email

Required, but never shown

StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fai.stackexchange.com%2fquestions%2f13633%2fwhich-approach-can-i-use-to-generate-text-based-on-multiple-inputs%23new-answer', 'question_page');
}
);

Post as a guest

Name

Email

Required, but never shown

2

$begingroup$

Generally, text generators work by modeling the joint distribution of the text by its Bayesian forward decomposition

$
begin{align*}
p(w_1, w_2, ..., w_n) &= p(w_1) * p(w_2|w_1) * p(w_3|w_2, w_1) * ... * p(w_n|{w_i}_{i<n})\
&= prod_{i=1}^n p(w_i|{w_k}_{k<i})\
end{align*}
$

From a modeling perspective, this looks right up RNN's ally, where you can have a state holding information from ${w_k}_{k<i}$ to learn a representation of $w_i$

Now, in your specific case, you're interested in a conditional text-generator, so you are trying to model $p(w_1, w_2, ..., w_n | {v_j}_j)$, but this same tactic works.

$
begin{align*}
p(w_1, w_2, ..., w_n| {v_j}_j) &= p(w_1|{v_j}_j) * p(w_2|w_1, {v_j}_j) * p(w_3|w_2, w_1, {v_j}_j) * ... * p(w_n|{w_i}_{i<n}, {v_j}_j)\
&= prod_{i=1}^n p(w_i|{w_k}_{k<i}, {v_j}_j)\
end{align*}
$

So, in your RNN or forward-based model, you can use the exact same approach just additionally embed the conditional inputs you have and somehow infuse it into the model (in practice, I have seen this through attention, concatenation, or some other common approach).

My recommendation (depending on the computational power you have) is to take advantage of the recent fad of pre-trained language models. Specifically, ones trained on next word prediction will probably do the job best. A good example is gpt-2, and, if you check out their GitHub, their code is very readable and easy to adjust for adding conditional input in the ways I have described.

share|improve this answer

edited 6 hours ago

nbro

5,68844 gold badges1515 silver badges3232 bronze badges

answered 8 hours ago

mshlismshlis

93511 silver badge1414 bronze badges

$endgroup$

add a comment | 

2

$begingroup$

Generally, text generators work by modeling the joint distribution of the text by its Bayesian forward decomposition

$
begin{align*}
p(w_1, w_2, ..., w_n) &= p(w_1) * p(w_2|w_1) * p(w_3|w_2, w_1) * ... * p(w_n|{w_i}_{i<n})\
&= prod_{i=1}^n p(w_i|{w_k}_{k<i})\
end{align*}
$

From a modeling perspective, this looks right up RNN's ally, where you can have a state holding information from ${w_k}_{k<i}$ to learn a representation of $w_i$

Now, in your specific case, you're interested in a conditional text-generator, so you are trying to model $p(w_1, w_2, ..., w_n | {v_j}_j)$, but this same tactic works.

$
begin{align*}
p(w_1, w_2, ..., w_n| {v_j}_j) &= p(w_1|{v_j}_j) * p(w_2|w_1, {v_j}_j) * p(w_3|w_2, w_1, {v_j}_j) * ... * p(w_n|{w_i}_{i<n}, {v_j}_j)\
&= prod_{i=1}^n p(w_i|{w_k}_{k<i}, {v_j}_j)\
end{align*}
$

So, in your RNN or forward-based model, you can use the exact same approach just additionally embed the conditional inputs you have and somehow infuse it into the model (in practice, I have seen this through attention, concatenation, or some other common approach).

My recommendation (depending on the computational power you have) is to take advantage of the recent fad of pre-trained language models. Specifically, ones trained on next word prediction will probably do the job best. A good example is gpt-2, and, if you check out their GitHub, their code is very readable and easy to adjust for adding conditional input in the ways I have described.

share|improve this answer

edited 6 hours ago

nbro

5,68844 gold badges1515 silver badges3232 bronze badges

answered 8 hours ago

mshlismshlis

93511 silver badge1414 bronze badges

$endgroup$

add a comment | 

$begingroup$

Generally, text generators work by modeling the joint distribution of the text by its Bayesian forward decomposition

$
begin{align*}
p(w_1, w_2, ..., w_n) &= p(w_1) * p(w_2|w_1) * p(w_3|w_2, w_1) * ... * p(w_n|{w_i}_{i<n})\
&= prod_{i=1}^n p(w_i|{w_k}_{k<i})\
end{align*}
$

From a modeling perspective, this looks right up RNN's ally, where you can have a state holding information from ${w_k}_{k<i}$ to learn a representation of $w_i$

Now, in your specific case, you're interested in a conditional text-generator, so you are trying to model $p(w_1, w_2, ..., w_n | {v_j}_j)$, but this same tactic works.

$
begin{align*}
p(w_1, w_2, ..., w_n| {v_j}_j) &= p(w_1|{v_j}_j) * p(w_2|w_1, {v_j}_j) * p(w_3|w_2, w_1, {v_j}_j) * ... * p(w_n|{w_i}_{i<n}, {v_j}_j)\
&= prod_{i=1}^n p(w_i|{w_k}_{k<i}, {v_j}_j)\
end{align*}
$

So, in your RNN or forward-based model, you can use the exact same approach just additionally embed the conditional inputs you have and somehow infuse it into the model (in practice, I have seen this through attention, concatenation, or some other common approach).

My recommendation (depending on the computational power you have) is to take advantage of the recent fad of pre-trained language models. Specifically, ones trained on next word prediction will probably do the job best. A good example is gpt-2, and, if you check out their GitHub, their code is very readable and easy to adjust for adding conditional input in the ways I have described.

share|improve this answer

edited 6 hours ago

nbro

5,68844 gold badges1515 silver badges3232 bronze badges

answered 8 hours ago

mshlismshlis

93511 silver badge1414 bronze badges

$endgroup$

share|improve this answer

edited 6 hours ago

nbro

5,68844 gold badges1515 silver badges3232 bronze badges

answered 8 hours ago

mshlismshlis

93511 silver badge1414 bronze badges

edited 6 hours ago

nbro

5,68844 gold badges1515 silver badges3232 bronze badges

edited 6 hours ago

nbro

5,68844 gold badges1515 silver badges3232 bronze badges

answered 8 hours ago

mshlismshlis

93511 silver badge1414 bronze badges

answered 8 hours ago

mshlismshlis

93511 silver badge1414 bronze badges