EUVIMEDEUVIMED entdecken
Crossref

On the Explainability of Natural Language Processing Deep Models

Julia El Zini, Mariette Awad

ACM Computing Surveys · 31.05.2023 · 55 (5) · 1-31

DOI: 10.1145/3529755 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 03.12.2022. Verfasst von Julia El Zini und 1 weiteren Autor:innen. Die Arbeit wurde bisher 111-mal zitiert (Crossref) und nennt 129 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Despite their success, deep networks are used as black-box models with outputs that are not easily explainable during the learning and the prediction phases. This lack of interpretability is significantly limiting the adoption of such models in domains where decisions are critical such as the medical and legal fields. Recently, researchers have been interested in developing methods that help explain individual decisions and decipher the hidden representations of machine learning models in general and deep networks specifically. While there has been a recent explosion of work on Explainable Artificial Intelligence (ExAI) on deep models that operate on imagery and tabular data, textual datasets present new challenges to the ExAI community. Such challenges can be attributed to the lack of input structure in textual data, the use of word embeddings that add to the opacity of the models and the difficulty of the visualization of the inner workings of deep models when they are trained on textual data. Lately, methods have been developed to address the aforementioned challenges and present satisfactory explanations on Natural Language Processing (NLP) models. However, such methods are yet to be studied in a comprehensive framework where common challenges are properly stated and rigorous evaluation practices and metrics are proposed. Motivated to democratize ExAI methods in the NLP field, we present in this work a survey that studies model-agnostic as well as model-specific explainability methods on NLP models. Such methods can either develop inherently interpretable NLP models or operate on pre-trained models in a post hoc manner. We make this distinction and we further decompose the methods into three categories according to what they explain: (1) word embeddings (input level), (2) inner workings of NLP models (processing level), and (3) models’ decisions (output level). We also detail the different evaluation approaches interpretability methods in the NLP field. Finally, we present a case-study on the well-known neural machine translation in an appendix, and we propose promising future research directions for ExAI in the NLP field.

Zitieren

APA

Zini, J. E., & Awad, M. (2023). On the Explainability of Natural Language Processing Deep Models. ACM Computing Surveys, 55(5), 1-31. https://doi.org/10.1145/3529755

Vancouver

Zini JE, Awad M. On the Explainability of Natural Language Processing Deep Models. ACM Computing Surveys. 2023;55(5):1-31. doi:10.1145/3529755

BibTeX
@article{Zini2023,
  author = {Zini, Julia El and Awad, Mariette},
  title = {On the Explainability of Natural Language Processing Deep Models},
  journal = {ACM Computing Surveys},
  year = {2023},
  volume = {55},
  number = {5},
  pages = {1--31},
  doi = {10.1145/3529755}
}
Kostenlos starten →