Overview
Who this competition fits
适合已经能训练或微调中文 NLP 模型、希望做机器阅读理解的学习者。参赛者需要能处理长篇中文文章,并具备一定的中学语文阅读能力,尤其要面对古诗文、现代文及字词理解、概括、推理和情感分析类问题。
Read the original official blurb
本任务源自中学语文阅读理解题,包含了古诗文和现代文,涉及字词的理解,段落总结,逻辑推理,情感分析以及创作背景等各个方面,以期推进中文自然语言处理的发展。 Official tags: 阅读理解. Sign-ups: 229.
Resources
What this competition gives you
There is a baseline you can run as-is — starting from it is usually far faster than building from scratch.
- BaselineNCR baseline system repository
- DataNCR Chinese reading-comprehension dataset: 8,388 articles and 20,477 questions
- Reference paperReference paper on the Native Chinese Reader dataset
- Support channelTechnical discussion group for contestant communication
- MentoringOrganiser staff provide periodic group Q&A
Preparation
From registration to a first submission
- 01
中文自然语言处理
- 02
机器阅读理解
- 03
长文本建模
- 04
古诗文与现代文阅读
- 05
JSON 数据处理
- 06
CSV 预测结果生成
Before you commit: 主要难点是从平均长度为 1024 的文章中提取与问题相关的信息,并在古诗文和现代文混合材料上完成细粒度理解与四选一判断。提交时还需按每个问题的 Q_id 生成可识别的 CSV 预测文件,且不能直接提交或高度复现基线预测结果。
Source
How this page was assembled
Competition information is structured from the official page. Scores are platform estimates for decision support; official rules take precedence.
- Official competition page
- Baidu AI Studio
- Last checked
- Not recorded