WikiLingua: A New Benchmark Dataset for Multilingual Abstractive Summarization.
Faisal LadhakEsin DurmusClaire CardieKathleen R. McKeownPublished in: EMNLP (Findings) (2020)
Keyphrases
- benchmark datasets
- digital libraries
- summary generation
- multi document summarization
- language independent
- cross language information retrieval
- automatic summarization
- multi lingual
- text summarization
- cross language
- cross lingual
- pedestrian detection
- neural network
- data sets
- text mining
- multi class
- terms of classification accuracy
- log analysis
- object recognition
- multimedia
- extractive summarization