Robustness in Natural Language Processing: Addressing Challenges in Text-based AI Systems

Though natural language processing (NLP) has developed prototype models that can handle a range of language events and navigate through adversarial situations, the discipline has made significant progress in the last few years in several linguistic tasks. However, the robustness of AI mechanisms tha...

Full description

Saved in:
Bibliographic Details
Published in2024 11th International Conference on Computing for Sustainable Global Development (INDIACom) pp. 1435 - 1439
Main Authors Rajchandar, K, Manoharan, Geetha, Ashtikar, Sunitha Purushottam
Format Conference Proceeding
LanguageEnglish
Published Bharati Vidyapeeth, New Delhi 28.02.2024
Subjects
Crops
LIME
Linguistics
Natural language processing
Navigation
Prototypes
SHAP
Speech Models
Speech Recognition
Text Based AI Systems
Text recognition
Text to Speech
Training
Online AccessGet full text
DOI10.23919/INDIACom61295.2024.10498289

Cover

More Information
Summary:Though natural language processing (NLP) has developed prototype models that can handle a range of language events and navigate through adversarial situations, the discipline has made significant progress in the last few years in several linguistic tasks. However, the robustness of AI mechanisms that parse text has been a serious source of concern. This study makes an effort to address the issues that crop up with NLP methodologies. Examining these study limits will enable us to pinpoint areas where the existing NLP systems need to be improved. Currently, the designs and training paradigms of the NLP models in use are thoroughly scrutinized and reviewed.
DOI:10.23919/INDIACom61295.2024.10498289