A Survey of the State of Explainable AI for Natural Language Processing

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Danilevsky, Marina, Qian, Kun, Aharonov, Ranit, Katsis, Yannis, Kawas, Ban, Sen, Prithviraj
Natura: Preprint
Pubblicazione: 2020
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916689229119488
author Danilevsky, Marina
Qian, Kun
Aharonov, Ranit
Katsis, Yannis
Kawas, Ban
Sen, Prithviraj
author_facet Danilevsky, Marina
Qian, Kun
Aharonov, Ranit
Katsis, Yannis
Kawas, Ban
Sen, Prithviraj
contents Recent years have seen important advances in the quality of state-of-the-art models, but this has come at the expense of models becoming less interpretable. This survey presents an overview of the current state of Explainable AI (XAI), considered within the domain of Natural Language Processing (NLP). We discuss the main categorization of explanations, as well as the various ways explanations can be arrived at and visualized. We detail the operations and explainability techniques currently available for generating explanations for NLP model predictions, to serve as a resource for model developers in the community. Finally, we point out the current gaps and encourage directions for future work in this important research area.
format Preprint
id arxiv_https___arxiv_org_abs_2010_00711
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle A Survey of the State of Explainable AI for Natural Language Processing
Danilevsky, Marina
Qian, Kun
Aharonov, Ranit
Katsis, Yannis
Kawas, Ban
Sen, Prithviraj
Computation and Language
Artificial Intelligence
Machine Learning
I.2.7
Recent years have seen important advances in the quality of state-of-the-art models, but this has come at the expense of models becoming less interpretable. This survey presents an overview of the current state of Explainable AI (XAI), considered within the domain of Natural Language Processing (NLP). We discuss the main categorization of explanations, as well as the various ways explanations can be arrived at and visualized. We detail the operations and explainability techniques currently available for generating explanations for NLP model predictions, to serve as a resource for model developers in the community. Finally, we point out the current gaps and encourage directions for future work in this important research area.
title A Survey of the State of Explainable AI for Natural Language Processing
topic Computation and Language
Artificial Intelligence
Machine Learning
I.2.7
url https://arxiv.org/abs/2010.00711