LCSTS (Large-scale Chinese Short Text Summarization)

Chinese short-text summarization from Sina Weibo author summaries; OpenCompass scores the 725-pair test split with jieba-tokenized ROUGE.

Also known as: Large-scale Chinese Short Text Summarization

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.

Category	generation
Subcategory	Chinese Weibo short-text summarization (OpenCompass generation split)
Page status	active
Metric	jieba-tokenized ROUGE-1/2/L F-measure (OpenCompass)
Direction	higher_is_better
Unit	%
Dataset size	725
Dataset licence	Apache-2.0 on the ModelScope opencompass/LCSTS card; original 2015 release terms not restated there
Publisher	Harbin Institute of Technology (dataset); OpenCompass (harness config)

What it measures

LCSTS asks a model to write a short Chinese summary of a Sina Weibo post. Gold summaries were written by the post author, not by a third-party abstractor. OpenCompass feeds the post text and scores the generated line against that author summary. Character-level Chinese, generation, not multiple choice.

Task format

OpenCompass LCSTSDataset, abbreviation lcsts, path opencompass/LCSTS. Zero-shot GenInferencer. Default config lcsts_gen.py includes lcsts_gen_8ee1fe (chat-style HUMAN prompt). Alternate lcsts_gen_9b0b89 uses a single string template. Evaluator JiebaRougeEvaluator.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub