Questions tagged [text-generation]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
0
votes
2answers
24 views

Distinguish randomly generated texts from reasonable for human texts

I have strings short texts of 2 types: '23jd2032n0d2mn', 'fn830n30rn83', 'fhui29n4ok', 'qn4foml', ... and ...
0
votes
1answer
25 views

Based on transformer, how to improve the text generation results?

If I do not pretrain the text generation model like BART, how to improve the result based on transformer like tensor2tensor? What are the improvement ideas for transformer in text generation task?
0
votes
0answers
13 views

How to build model(s) for simulating conversations between two parties?

I'm working on a problem for chat based buying and selling of products. Due to lack of training data I most likely have to use synthetic data. I was trying to come up with ways to do that, but so far ...
0
votes
1answer
11 views

Question of pretraining text-generation task, it seems that pretraining is not work for a small model?

My task is to generate keywords from sentences. I pretrain a text-generation model. I mask the sentences' tokens and predict the whole sentences' tokens. Pretraining batch_size = 8 and step = 1000000 ...
1
vote
2answers
23 views

Generation of institution names

I have found a number of parsers for the automatic extraction of institution names from texts (e.g. this one). My task is in a sense the inverse one: I want to automatically generate reality-like ...
1
vote
1answer
18 views

Generate text using user-supplied keywords

I've got a use case where I need to generate sentences based on a set of user supplied keywords. Here is an example of what I need: User input: End-User: Data Scientists Region: Middle East ...
0
votes
0answers
20 views

Reward Function for NLP

I would like to design an reward function , I am training two models from the first model that classify set of texts(paragraphs and keywords) and I also got some hidden states. The second model is ...
0
votes
1answer
24 views

Is it a Problem if Training Data and Evaluation Data are Very Similar?

I'm working on a group project where we have decided to use this Microsoft WIP repository as our starting point. It's a project which compares different frameworks and models and their ability to do ...
0
votes
0answers
8 views

Looking for suggestions on performing Sementic Analysis of ASR text

Currently I am working on a project where I have ASR on which I am performing semantic analysis to extract meaning out of it. The ASR text contains huge amount of vague conversational text which needs ...
0
votes
0answers
25 views

Calculating Top k Text prediction using Tensorflow

I would like to adapt the code of PTB Tensorflow code [https://github.com/tensorflow/models/blob/master/tutorials/rnn/ptb/ptb_word_lm.py], in order to calculate top k predicted word samples, on the ...
2
votes
2answers
33 views

How to generate a sentence with exactly N words?

Thanks to GPT2 pretrained model now it is possible to generate meaningful sequence of words with or without prefix. However a sentence should end with a proper endings (.,!,?). I am just wondering how ...
0
votes
0answers
13 views

LSTM's with variable size input features + how to do embeddings with (x,y) coordinate systems

Background : So I have a dataset of x,y positions of dancers dancing("doin' their thang!!"). Some sequences of the dance are with 8, some with 5,4,8, upto 16. So, I am trying to do something like ...
1
vote
0answers
38 views

Paraphrase Generation - state-of-the-art?

I need to paraphrase short, but abstract sentences, such as: He prefers variety to routine. or I am easily discouraged. I've played around couple of online tools (such as https://quillbot.com/)...
0
votes
0answers
27 views

Pretrained Models for Keyword-Based Text Generation

I'm looking for an implementation that allows me to generate text based on a pre-trained model (e.g. GPT-2). An example would be gpt-2-keyword-generation (click here for demo). As the author notes, ...
0
votes
0answers
6 views

Generation of Hypotheses for Textual Entailment

Recent developments in NLP have shown good results in recognizing textual entailment (RTE, GLUE Benchmark). For those unfamiliar with the subject, an example of a text that entails a hypothesis would ...
0
votes
1answer
38 views

predicting next jobtitle

I have a dataset of which has 30M rows each like [current_jobtitles, nextjobtitles]. ...
4
votes
1answer
111 views

NLP - paraphrase extraction in python

I am trying to develop a NLP model, which takes something like you have high levels of cholesterol(this will be a tag) as input and has to output something like <...
2
votes
1answer
37 views

Create an RNN on text sources with different lengths

I want to create an RNN to generate a new text based on many examples of existing texts of a certain format in the training data. The type of texts in the training data consists of 3 segments, like so:...
0
votes
0answers
32 views

How to build a OCR for reading text from image?

This is my first time working on a OCR application. I have lot of scanned images of English text-book pages like this and I want to build a OCR using DL to ...
2
votes
1answer
27 views

Automatic data summarization with text

I would like to automate periodic report writing based on data. Given one/some data tables, the machine should output texts like ...
3
votes
1answer
199 views

Choosing the size of Character Embedding for Language Generation models

I am working on a character-based Language Generator, loosely based on this tutorial on the TensorFlow 2.0 website. Following the example, I am using an Embedding() ...
0
votes
1answer
252 views

Can BERT/ELMo be used (or retrained) to generate a text in both directions?

Text generation is perhaps one of the fun things to do with old NGram or new BERT/ELMo models. I am wondering can BERT be used to generate text from the end of a sentence, or better in both directions....
0
votes
0answers
14 views

Conceptual help generating a text adventure game using a GAN

I have built a playable dungeon crawler game that lets a character progress through a series of randomly generated rooms filled with doors, chests, stairs, etc. Ideally, I would be able to display a ...
1
vote
1answer
2k views

Distractor Generation for Multiple Choice Questions

I'm currently working on generating distractor for multiple choice questions. Training set consists of question, answer and 3 distractor and I need to predict 3 distractor for test set. I have gone ...
2
votes
0answers
24 views

Back-Translation model for German and English

Do you know of any pre-trained models for back translation between German and English? I am aware that there are ways to include a monolingual corpus into the training of a machine translation model (...
1
vote
1answer
215 views

Is it possible to use Word2vec for text paraphrasing?

After reading several papers I am not sure if it is possible to some how generate text with the same meaning (paraphrase it) using only Word2vec. I found out other approaches that use sequences of ...
1
vote
0answers
78 views

Generate sentences using given data [closed]

I am working on an automated insights generation use case where I want to generate meaningful sentences from given aggregated data. For example, Data: ...
0
votes
1answer
550 views

Which is better: GPT or RelGAN for text generation?

Based on my understanding, gpt or gpt-2 are using language model loss to train and generate text, which do not contains GAN. So which is better: GPT vs RelGAN/LeakGAN/SeqGAN/TextGAN I am so ...
2
votes
0answers
33 views

How to prepare the data for text generation task

First, I'm not sure whether the model contains the encoder during training. EOS means end-of-sentence. Encoder and decoder are part of transformer network. If without-encoder, training time: ...
-1
votes
1answer
233 views

What is the difference between TextGAN and LM for text generation?

I'm new to LeakGAN or SeqGAN or TextGAN. I know GAN is to generate text and let discriminator un-judge-able to real text and gen-text. LM(language model) is the task of predicting the next word and ...
2
votes
1answer
207 views

NLP text autoencoder that generates text in poetic meter

I would like to create an NLP autoencoder that happens to only generate text that conforms to a poetic meter, for example 'iambic pentameter'. That is, the output should be a series of clauses which ...
1
vote
0answers
17 views

Current state of art approaches in generating features based on other available features and items

I am about to do a project that is about generating texts for missing entries that are related to some object (using information about other available entries related to the same object and ...
3
votes
2answers
76 views

What NN architecture to predict fantasy character names based on description?

I would like to build a neural network to predict a fantasy character name given a description. Like 'Scar-faced long haired elf warrior' -> 'Glorfindel' I have a dataset of about 12,000 fantasy ...
1
vote
0answers
30 views

Training a LSTM on two merged writing styles (say Shakespeare and Frost)

I was trying to develop intuitions on how two writing styles can be merged (if at all they can be merged) into a single LSTM and then get meaningful results from the same. Can anybody provide me ...
4
votes
1answer
204 views

Can someone please explain what this sample function is upto?

So there is a function in Dino_Name_Generator at Deeplearning.ai notebook ...
0
votes
1answer
34 views

Which NN architecture solves my problem?

I want to convert images frame into text, for instance, if I have a image with a dog that plays with a ball I will produce a simple text "Dog plays with ball" (Ok, I know I must have x samples ...
1
vote
0answers
428 views

Why use GAN in NLG?

I am interested in the GAN recently. There are many papers that recently applied GAN to NLG. I do not know much about NLP or NLG, but I wonder why I use GAN for NLG. For better quality? Or for many ...
2
votes
1answer
922 views

Gumbel Softmax vs Vanilla Softmax for GAN training

When training a GAN for text generation, i have seen many people feeding the gumbel-softmax from the generator output and feed into the discriminator. This is to bypass the problem of having to sample ...
1
vote
0answers
276 views

Neural network outputting same result for all inputs

I'm building an encoder-decoder neural network in Keras for sequence generation. The specific task is to try and change the styles of the text. Both my encoder and decoders are LSTMs with latent ...
1
vote
2answers
80 views

How should I format input and output for text generation with LSTMs

I'm attempting to generate a response to an input line of text using an LSTM. I've considered various forms of input, including one-hot encoding each character in the line and passing each input line ...
3
votes
1answer
138 views

Choosing a right algorithm for template-based text generation

I am doing a text generation project -- the task is to basically represent the statistical data in a readable way. The way I decided to go about this is template-based: each data type has a template ...
3
votes
0answers
856 views

Help with the following error: Variable already exists, disallowed. Did you mean to set reuse=True in VarScope?

I am not sure how to handle this error. This is from an RNN tutorial found here. I vaguely understand that the variables need to be able to be reused, but I don't know how to implement this fix. ...
1
vote
1answer
105 views

Text generation using Tensor Factorization

Text generation is well studied using Markov chains or NNs, but I am not aware of any works to word sequence prediction in terms of subspace learning. Treating phrases or sentences as temporal data ...
4
votes
1answer
987 views

From regression neural network to generative one

I made a neural network with word embedding, RNN and some dense layers to predict the score of computer game reviews based on the title of the game. I used Keras in Python. I was wondering if it would ...
1
vote
1answer
323 views

Given one language ngram model, how do I compare likelihoods of two texts of different length?

Let's say I have conditional probabilities estimates for N-grams and I want to find out which of the two sequences of different length 'looks more natural' in terms of the given model. How does one ...
0
votes
1answer
796 views

Learning character sequences and predicting sequences

I'm novice to deep learning and sorry if these questions may look very basic. ******************* First Question ******************* I need to predict the next k-characters given some initial text ...
1
vote
0answers
265 views

Hyper-parameters for character-level RNN models

I am try to recreate Karpathy's great tutorial on RNN character-level text generation using TensorFlow - Promise to contribute the code back to the community once it works. Meanwhile, my code runs, ...