Reassessing Evaluation Practices in Visual Question Answering: A Case Study on Out-of-Distribution Generalization.
Aishwarya AgrawalIvana KajicEmanuele BugliarelloElnaz DavoodiAnita GergelyPhil BlunsomAida NematzadehPublished in: EACL (Findings) (2023)
Keyphrases
- question answering
- information retrieval
- natural language processing
- information extraction
- named entities
- natural language
- qa clef
- question classification
- passage retrieval
- natural language questions
- cross language
- relation extraction
- answer validation
- answering questions
- open domain question answering
- syntactic information
- question answering systems
- low level
- evaluation criteria
- evaluation methods
- qa systems
- evaluation metrics
- sentence retrieval
- evaluation method
- multi modal
- machine learning