Towards Explainable Evaluation Metrics for Natural Language Generation.
Christoph LeiterPiyawat LertvittayakumjornMarina FomichevaWei ZhaoYang GaoSteffen EgerPublished in: CoRR (2022)
Keyphrases
- information retrieval
- natural language generation
- evaluation metrics
- learning to rank
- precision and recall
- average precision
- dialog systems
- dialogue system
- natural language
- text generation
- machine translation
- information extraction
- evaluation measures
- search engine
- natural language processing
- evaluation framework
- word order
- aggregated search
- relevance feedback
- data mining
- artificial intelligence
- vector space
- relevance judgments
- knowledge representation