MoverScore: Evaluating text generation with contextualized embeddings and earth mover distance
Project description
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
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
moverscore-1.0.3.tar.gz
(7.7 kB
view details)
File details
Details for the file moverscore-1.0.3.tar.gz
.
File metadata
- Download URL: moverscore-1.0.3.tar.gz
- Upload date:
- Size: 7.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.15.0 pkginfo/1.4.2 requests/2.18.4 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.30.0 CPython/2.7.15
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 99be483d512d4548a2191543f8c7dd6727d83163f92ded2d1958657b177479b8 |
|
MD5 | bae152b4d93bf5e8429db331d734e0f6 |
|
BLAKE2b-256 | d7665ac942903a4d2d316f6c1df716e047e34fb0f9bfc7e70d44dab995708e9d |