What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability
Submission Type: Regular Long Paper
Submission Track: Interpretability, Interactivity, and Analysis of Models for NLP
Submission Track 2: Language Modeling and Analysis of Language Models
Keywords: uncertainty, NLG, variability, language production, text generation
TL;DR: We propose a statistical framework to assess sequence-level uncertainty in text generators against plausible response variability in humans and perform an empirical study on four NLG tasks.
Abstract: In Natural Language Generation (NLG) tasks, for any input, multiple communicative goals are plausible, and any goal can be put into words, or produced, in multiple ways. We characterise the extent to which human production varies lexically, syntactically, and semantically across four NLG tasks, connecting human production variability to aleatoric or data uncertainty. We then inspect the space of output strings shaped by a generation system's predicted probability distribution and decoding algorithm to probe its uncertainty. For each test input, we measure the generator's calibration to human production variability. Following this instance-level approach, we analyse NLG models and decoding strategies, demonstrating that probing a generator with multiple samples and, when possible, multiple references, provides the level of detail necessary to gain understanding of a model's representation of uncertainty.
Submission Number: 3289
Loading