DeepAI AI Chat
Log In Sign Up

Decoding Methods for Neural Narrative Generation

by   Alexandra DeLucia, et al.

Narrative generation is an open-ended NLP task in which a model generates a story given a prompt. The task is similar to neural response generation for chatbots; however, innovations in response generation are often not applied to narrative generation, despite the similarity between these tasks. We aim to bridge this gap by applying and evaluating advances in decoding methods for neural response generation to neural narrative generation. In particular, we employ GPT-2 and perform ablations across nucleus sampling thresholds and diverse decoding hyperparameters—specifically, maximum mutual information—analyzing results over multiple criteria with automatic and human evaluation. We find that (1) nucleus sampling is generally best within 0.7 ≤ p ≤ 0.9; (2) a maximum mutual information objective can improve the quality of generated stories; and (3) established automatic metrics do not correlate well with human judgments of narrative quality on any qualitative metric.


page 1

page 2

page 3

page 4


Diverse Melody Generation from Chinese Lyrics via Mutual Information Maximization

In this paper, we propose to adapt the method of mutual information maxi...

A Simple, Fast Diverse Decoding Algorithm for Neural Generation

In this paper, we propose a simple, fast decoding algorithm that fosters...

MIND: Maximum Mutual Information Based Neural Decoder

We are assisting at a growing interest in the development of learning ar...

Neural Response Generation with Dynamic Vocabularies

We study response generation for open domain conversation in chatbots. E...

Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation

Research on Automatic Story Generation (ASG) relies heavily on human and...

Trading Off Diversity and Quality in Natural Language Generation

For open-ended language generation tasks such as storytelling and dialog...

Non-Autoregressive Neural Dialogue Generation

Maximum Mutual information (MMI), which models the bidirectional depende...