1 |
Natural Language Statistical Features of LSTM-generated Texts ...
|
|
|
|
Abstract:
Long Short-Term Memory (LSTM) networks have recently shown remarkable performance in several tasks dealing with natural language generation, such as image captioning or poetry composition. Yet, only few works have analyzed text generated by LSTMs in order to quantitatively evaluate to which extent such artificial texts resemble those generated by humans. We compared the statistical structure of LSTM-generated language to that of written natural language, and to those produced by Markov models of various orders. In particular, we characterized the statistical structure of language by assessing word-frequency statistics, long-range correlations, and entropy measures. Our main finding is that while both LSTM and Markov-generated texts can exhibit features similar to real ones in their word-frequency statistics and entropy measures, LSTM-texts are shown to reproduce long-range correlations at scales comparable to those found in natural language. Moreover, for LSTM networks a temperature-like parameter ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://dx.doi.org/10.48550/arxiv.1804.04087 https://arxiv.org/abs/1804.04087
|
|
BASE
|
|
Hide details
|
|
2 |
Complexity and universality in the long-range order of words ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Beyond the Zipf-Mandelbrot law in quantitative linguistics ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Entropic analysis of the role of words in literary texts ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|