MoverScore: Evaluating text generation with contextualized embeddings and earth mover distance
Project Links
Meta
Author: Wei Zhao
Requires Python: >=3
Classifiers
Development Status
- 5 - Production/Stable
Intended Audience
- Developers
- Science/Research
Topic
- Scientific/Engineering
- Scientific/Engineering :: Artificial Intelligence
- Text Processing
License
- OSI Approved :: Apache Software License
Programming Language
- Python :: 3 :: Only
MoverScore is a semantic-based evaluation metric for text generation tasks, e.g., machine translation, text summarization, image captioning, question answering and etc, where the system and reference texts are encoded by contextualized word embeddings finetuned on Multi-Natural-Language-Inference, then the Earth Mover Distance is leveraged to compute the semantic distance by comparing two sets of embeddings resp. to the system and reference text
Files in release
No dependencies