Project description

TiGEr-Eval: Text Generation Evaluation Toolkit

TiGEr toolkit for text generation evaluation.

pip install tiger-eval

pip install .

The toolkit should support various metrics

ROUGE, BLEU
Model based: BERTScore, BLEURT
Open Generation, need to be further improved
For multichoice questions. Other matching techniques? E.g. use model to reformat the answer?

These details have not been verified by PyPI

View statistics for this project via Libraries.io, or by using our public dataset on Google BigQuery

This version

0.0.2

Dec 19, 2023

0.0.1

Dec 15, 2023

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Uploaded Dec 19, 2023 Source

Uploaded Dec 19, 2023 Python 3

Hashes for tiger_eval-0.0.2.tar.gz
Algorithm	Hash digest
SHA256	`32d1b6d0b73f705a5941af5aca4a2d155e32368816460bbba28019af2f6c89d7`
MD5	`dc10946d1181f79b24256cb87208cd7a`
BLAKE2b-256	`2ac9a501efc3be6cf3feb96306b4590f88b5144d43076b5f48f7f9d2fdf666e4`

Hashes for tiger_eval-0.0.2-py3-none-any.whl
Algorithm	Hash digest
SHA256	`69b09fd352f3e5c44032fc966912675956ea14df954c27cdd84c39064362a6d8`
MD5	`09339da1bc8bb9e3357e28a4c1b4db03`
BLAKE2b-256	`0b5bbf9ef598d39c8f2d2500bd3f029dc629701fbb4f7098139bed414fd7ee16`