chakki-works/sumeval
Well tested & Multi-language evaluation framework for text summarization.
Implements ROUGE, BLEU, and ROUGE-BE metrics with validation against original reference implementations (Perl ROUGE-1.5.5 and official WMT mteval scripts). Supports English, Japanese, and Chinese through language-specific tokenizers (janome/MeCab for Japanese, jieba for Chinese) with optional dependency parsing via spaCy and GiNZA. Available as a pure Python library with CLI interface for batch evaluation.
625 stars and 2,803 monthly downloads. Used by 1 other package. No commits in the last 6 months. Available on PyPI.
Stars
625
Forks
58
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 15, 2022
Monthly downloads
2,803
Commits (30d)
0
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/chakki-works/sumeval"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
zhang17173/Event-Extraction
基于法律裁判文书的事件抽取及其应用，包括数据的分词、词性标注、命名实体识别、事件要素抽取和判决结果预测等内容
wasiahmad/paraphrase_identification
Examine two sentences and determine whether they have the same meaning.
thuiar/TEXTOIR
TEXTOIR is the first opensource toolkit for text open intent recognition. (ACL 2021)
artitw/BERT_QA
Accelerating the development of question-answering systems based on BERT and TF 2.0
victordibia/neuralqa
NeuralQA: A Usable Library for Question Answering on Large Datasets with BERT