recentpopularlog in

text-generation

TheBerkin/rant: Rant – The all-purpose procedural text library
Rant – The all-purpose procedural text library. Contribute to TheBerkin/rant development by creating an account on GitHub.
text-generation  library 
yesterday by gzfrancisco
GitHub - TheBerkin/rant: Rant – The all-purpose procedural text library
Rant – The all-purpose procedural text library. Contribute to TheBerkin/rant development by creating an account on GitHub.
procedural  text-generation 
3 days ago by synergyfactor
TheBerkin/rant: Rant – The all-purpose procedural text library
Rant – The all-purpose procedural text library. Contribute to TheBerkin/rant development by creating an account on GitHub.
generativetext  text-generation  procedural 
9 days ago by erzwinkel
TheBerkin/rant: Rant – The all-purpose procedural text library
Rant – The all-purpose procedural text library. Contribute to TheBerkin/rant development by creating an account on GitHub.
procedural  text-generation  algorithm  github  library 
9 days ago by hthief
udibr/headlines: Automatically generate headlines to short articles
"This project attempts to reproduce the results in the paper: Generating News Headlines with Recurrent Neural Networks"
papers  rnn  keras  examples  nlp  text  text-generation  generative  generative-models 
april 2016 by arsyed
[1601.03313] Political Speech Generation
In this report we present a system that can generate political speeches for a desired political party. Furthermore, the system allows to specify whether a speech should hold a supportive or opposing opinion. The system relies on a combination of several state-of-the-art NLP methods which are discussed in this report. These include n-grams, Justeson & Katz POS tag filter, recurrent neural networks, and latent Dirichlet allocation. Sequences of words are generated based on probabilities obtained from two underlying models: A language model takes care of the grammatical correctness while a topic model aims for textual consistency. Both models were trained on the Convote dataset which contains transcripts from US congressional floor debates. Furthermore, we present a manual and an automated approach to evaluate the quality of generated speeches. In an experimental evaluation generated speeches have shown very high quality in terms of grammatical correctness and sentence transitions.
papers  speech  text-generation  nlp  generative  generative-models 
february 2016 by arsyed
A Tour Through Random Ruby
turns out Ruby has a good set of random-text-generation gems on offer
random  ruby  coding  text-generation  markov-chain  gems 
july 2015 by jm
Des robots au « Monde » pendant les élections départementales ? Oui… et non | Back Office
Des robots au « Monde » pendant les élections départementales ? Oui… et non via @lemondefr et @syllabs
lemonde  syllabs  text-generation 
march 2015 by ronnix

Copy this bookmark:





to read