bleurt
NLG evaluation metric
An evaluation metric for Natural Language Generation based on transfer learning.
BLEURT is a metric for Natural Language Generation based on transfer learning.
705 stars
13 watching
85 forks
Language: Python
last commit: over 2 years ago
Linked from 1 awesome list
accelerated-text/awesome-nlgRelated projects:
| Repository | Description | Stars |
|---|---|---|
 maluuba/nlg-eval | A toolset for evaluating and comparing natural language generation models | 1,350 |
 benhamner/metrics | Provides implementations of various supervised machine learning evaluation metrics in multiple programming languages. | 1,632 |
 mlgroupjlu/llm-eval-survey | A repository of papers and resources for evaluating large language models. | 1,450 |
 bllip/bllip-parser | A statistical natural language parser used to generate grammatically correct sentences from unstructured text input. | 227 |
 microsoft/prophetnet | A collection of research implementations and models for natural language generation | 694 |
 i-gallegos/fair-llm-benchmark | Compiles bias evaluation datasets and provides access to original data sources for large language models | 115 |
 thiagocf05/webnlg | Provides intermediate representations of data for NLG tasks like Discourse Ordering and Lexicalization | 69 |
 nlgranger/seqtools | A Python library to manipulate and transform indexable data | 49 |
 dluebke/bpelstats | A tool for calculating and analyzing BPEL metrics | 0 |
 simplenlg/simplenlg | A Java API for generating natural language texts from syntactic forms | 810 |
 intellabs/fastrag | A framework for efficient and optimized retrieval augmented generative pipelines using state-of-the-art LLMs and Information Retrieval. | 1,392 |
 lartpang/pysodmetrics | A library providing an implementation of various metrics for object segmentation and saliency detection in computer vision. | 150 |
 opennlg/openba | A pre-trained language model designed for various NLP tasks, including dialogue generation, code completion, and retrieval. | 94 |
| google-research/deep_ope | Provides benchmarking policies and datasets for offline reinforcement learning | 85 |