Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing.
Sanchit SinhaHanjie ChenArshdeep SekhonYangfeng JiYanjun QiPublished in: BlackboxNLP@EMNLP (2021)
Keyphrases
- natural language processing
- information extraction
- natural language
- machine learning
- computational linguistics
- wordnet
- semantic analysis
- semantic relations
- text mining
- language processing
- text processing
- free text
- knowledge representation
- named entity recognition
- artificial intelligence
- text summarization
- named entities
- deep learning
- computational biology
- data sets
- word sense disambiguation
- knowledge base
- databases
- part of speech
- text classification
- real world
- database
- belief nets
- tasks in natural language processing