Sensitivity as a Complexity Measure for Sequence Classification Tasks

We introduce a theoretical framework for understanding and predicting the complexity of sequence classification tasks, using a novel extension of the theory of Boolean function sensitivity. The sensitivity of a function, given a distribution over input sequences, quantifies the number of disjoint su...

Full description

Saved in:
Bibliographic Details
Published in:Transactions of the Association for Computational Linguistics Vol. 9; pp. 891 - 908
Main Authors: Hahn, Michael, Jurafsky, Dan, Futrell, Richard
Format: Journal Article
Language:English
Published: One Rogers Street, Cambridge, MA 02142-1209, USA MIT Press 18.08.2021
MIT Press Journals, The
The MIT Press
Subjects:
Boolean functions
Classification
Classifiers
Decoders
Natural language processing
Representations
Sequences
Subsets
Task complexity
Task performance
ISSN:2307-387X, 2307-387X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We introduce a theoretical framework for understanding and predicting the complexity of sequence classification tasks, using a novel extension of the theory of Boolean function sensitivity. The sensitivity of a function, given a distribution over input sequences, quantifies the number of disjoint subsets of the input sequence that can each be individually changed to change the output. We argue that standard sequence classification methods are biased towards learning low-sensitivity functions, so that tasks requiring high sensitivity are more difficult. To that end, we show analytically that simple lexical classifiers can only express functions of bounded sensitivity, and we show empirically that low-sensitivity functions are easier to learn for LSTMs. We then estimate sensitivity on 15 NLP tasks, finding that sensitivity is higher on challenging tasks collected in GLUE than on simple text classification tasks, and that sensitivity predicts the performance both of simple lexical classifiers and of vanilla BiLSTMs without pretrained contextualized embeddings. Within a task, sensitivity predicts which inputs are hard for such simple models. Our results suggest that the success of massively pretrained contextual representations stems in part because they provide representations from which information can be extracted by low-sensitivity decoders.
Bibliography:2021
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2307-387X
2307-387X
DOI:10.1162/tacl_a_00403