Back to search

Georgia Institute of Technology

Interpreting Neural Networks for and with Natural Language

Abstract

dc:description.abstract

In the past decade, natural language processing (NLP) systems have come to be built almost exclusively on a backbone of large neural models. As the landscape of feasible tasks has widened due to the capabilities of these models, the space of applications has also widened to include subfields with real-world consequences, such as fact-checking, fake news detection, and medical decision support. The increasing size and nonlinearity of these models results in an opacity that hinders efforts by machine learning practitioners and lay-users alike to understand their internals and derive meaning or trust from their predictions. The fields of explainable artificial intelligence (XAI) and more specifically explainable NLP (ExNLP) have emerged as an active area for remedying this opacity and for ensuring models' reliability and trustworthiness in high-stakes scenarios, by providing textual explanations meaningful to human users. Models that produce justifications for their individual predictions can be inspected for the purposes of debugging, quantifying bias and fairness, understanding model behavior, and ascertaining robustness and privacy. Textual explanation is a predominant form of explanation in machine learning datasets regardless of task modality. As such, this dissertation covers both explaining tasks with natural language and explaining natural language tasks. In this dissertation, I propose test suites for evaluating the quality of model explanations under two definitions of meaning: faithfulness and human acceptability. I use these evaluation methods to investigate the utility of two explanation forms and three model architectures. I finally propose two methods to improve explanation quality– one which increases the likelihood of faithful highlight explanations and one which improves the human acceptability of free-text explanations. This work strives to increase the likelihood of positive use and outcomes when AI systems are deployed in practice.

Degree

thesis:*
Level thesis:degree_level
Doctoral
Department dc:contributor.department
Interactive Computing
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2022

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Wiegreffe, Sarah Augusta
Advisor dc:contributor.advisor
  • Riedl, Mark O.
Committee members dc:contributor.committeemember
  • Xu, Wei
  • Ritter, Alan
  • Smith, Noah A.
  • Singh, Sameer

Subjects

dc:subject × 4

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/1853/67202

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Wiegreffe, Sarah Augusta. Interpreting Neural Networks for and with Natural Language. Doctoral thesis, Georgia Institute of Technology, 2022. http://hdl.handle.net/1853/67202