Does External Knowledge Help Explainable Natural Language Inference? Automatic Evaluation vs. Human Ratings.
Hendrik SchuffHsiu-Yu YangHeike AdelNgoc Thang VuPublished in: BlackboxNLP@EMNLP (2021)
Keyphrases
- automatic evaluation
- external knowledge
- natural language
- human judgments
- domain knowledge
- wordnet
- semantic relatedness
- text categorization
- human subjects
- natural language processing
- quality assessment
- information extraction
- collaborative filtering
- artificial intelligence
- web directories
- machine learning
- document clustering
- textual information
- knowledge sources
- clustering algorithm
- training data
- word sense disambiguation
- active learning
- query expansion
- knowledge representation
- probabilistic model