Trading Off Diversity and Quality in Natural Language Generation

04/22/2020
by   Hugh Zhang, et al.
0

For open-ended language generation tasks such as storytelling and dialogue, choosing the right decoding algorithm is critical to controlling the tradeoff between generation quality and diversity. However, there presently exists no consensus on which decoding procedure is best or even the criteria by which to compare them. We address these issues by casting decoding as a multi-objective optimization problem aiming to simultaneously maximize both response quality and diversity. Our framework enables us to perform the first large-scale evaluation of decoding methods along the entire quality-diversity spectrum. We find that when diversity is a priority, all methods perform similarly, but when quality is viewed as more important, the recently proposed nucleus sampling (Holtzman et al. 2019) outperforms all other evaluated decoding algorithms. Our experiments also confirm the existence of the `likelihood trap', the counter-intuitive observation that high likelihood sequences are often surprisingly low quality. We leverage our findings to create and evaluate an algorithm called selective sampling which tractably approximates globally-normalized temperature sampling.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/22/2019

The Curious Case of Neural Text Degeneration

Despite considerable advancements with deep neural language models, the ...
research
10/25/2022

Information Filter upon Diversity-Improved Decoding for Diversity-Faithfulness Tradeoff in NLG

Some Natural Language Generation (NLG) tasks require both faithfulness a...
research
10/07/2022

An Analysis of the Effects of Decoding Algorithms on Fairness in Open-Ended Language Generation

Several prior works have shown that language models (LMs) can generate t...
research
10/13/2022

Language Model Decoding as Likelihood-Utility Alignment

A critical component of a successful language generation pipeline is the...
research
10/14/2020

Decoding Methods for Neural Narrative Generation

Narrative generation is an open-ended NLP task in which a model generate...
research
10/03/2022

A Non-monotonic Self-terminating Language Model

Recent large-scale neural autoregressive sequence models have shown impr...
research
02/26/2023

Tailoring Language Generation Models under Total Variation Distance

The standard paradigm of neural language generation adopts maximum likel...

Please sign up or login with your details

Forgot password? Click here to reset