| 1 |
Distributional Discrepancy: A Metric for Unconditional Text Generation ...
|
|
|
|
Abstract:
The purpose of unconditional text generation is to train a model with real sentences, then generate novel sentences of the same quality and diversity as the training data. However, when different metrics are used for comparing the methods of unconditional text generation, contradictory conclusions are drawn. The difficulty is that both the diversity and quality of the sample should be considered simultaneously when the models are evaluated. To solve this problem, a novel metric of distributional discrepancy (DD) is designed to evaluate generators based on the discrepancy between the generated and real training sentences. However, it cannot compute the DD directly because the distribution of real sentences is unavailable. Thus, we propose a method for estimating the DD by training a neural-network-based text classifier. For comparison, three existing metrics, bi-lingual evaluation understudy (BLEU) versus self-BLEU, language model score versus reverse language model score, and Fréchet embedding distance, ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2005.01282
https://dx.doi.org/10.48550/arxiv.2005.01282
|
|
BASE
|
|
Hide details
|
|
|
| 2 |
Integrating character representations into Chinese word embedding
|
|
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Distributional similarity for Chinese: exploiting characters and radicals
|
|
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Improved word similarity computation for Chinese using sub-word information
|
|
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Estimating and exploiting the entropy of sense distributions
|
|
|
|
BASE
|
|
Show details
|
|
|
| 8 |
FUZZY GROUP DECISION MAKING MODEL BASED ON CREDIBILITY THEORY AND GRAY RELATIVE DEGREE
|
|
|
|
BASE
|
|
Show details
|
|
|
| 9 |
FUZZY GROUP DECISION MAKING MODEL BASED ON CREDIBILITY THEORY AND GRAY RELATIVE DEGREE
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
