didi / chinesenlp

Datasets, SOTA results of every fields of Chinese NLP

Chinese NLP

Shared tasks, datasets and state-of-the-art results for Chinese Natural Language Processing (NLP)

Table of Tasks

• Co-reference Resolution
• Constituency Parsing
• Dialogue State Management
• Emotion Classification
• Entity Linking
• Entity Tagging
• Language Modeling
• Machine Translation
• Multi-task Learning
• Part-of-Speech (POS) Tagging
• Question Answering
• Relation Extraction
• Sentiment Analysis
• Simplified/Traditional Conversion
• Spell Correction
• Text Summarization
• Topic Classification
• Transliteration
• Word Embedding
• Word Segmentation

Besides Chinese NLP

To track more progress in Natural Language Processing (NLP) in English and other languages, you can check NLP-progress, which includes the datasets and the current state-of-the-art for the most common NLP tasks.

What's new!

We have a new shared task at this year's WMT titled "Triangular MT: Using English to improve Russian-to-Chinese machine translation". We would encourage you to participate in this shared task.

More details of the shared task is present at http://www.statmt.org/wmt21/triangular-mt-task.html

Please pass on the pointer to any of your colleagues and friends who might be interested in participating.

Important Dates

• Apr 5, 2021: Release of training and development resources
• Apr 5, 2021: Release of the baseline system
• Jul 12, 2021: Release of test data
• Jul 19, 2021: Official submissions due by web upload
• Jul 20, 2021: Release of the official results
• Aug 5, 2021: System description paper due
• Sep 5, 2021: Review feedback
• Sep 15, 2021: Camera-ready papers due
• Nov 10-11, 2021: Workshop

Contribute

Want to contribute? Please follow the Instructions

Contact

Suggestions? Changes? Please send email to [email protected]

Note

This project is initiated and actively maintained by DiDi NLP team under DiDi AI Labs.

chinesenlp's Issues

你好，可以分享一下LCSTS2.0原始数据集吗？

你好，可以分享一下LCSTS2.0原始数据集吗？我按官方的填写了申请，一直没有收到他们的回信，CSDN的链接也失效的，多谢。[email protected]

有机器阅读理解的吗？

如题，求更

Source code

How to access the source code for Relation Extraction. I could not find it in this repository.

请问有收集 基于aspect的情感分析 的相关资料吗？

请问有收集 基于aspect的情感分析 的相关资料吗？

有可以玩的 demo 网页？

如题

咨询co-reference_resolution.md的问题

请问您在共指消解上实现的输入输出是这篇《Deep Reinforcement Learning for Mention-Ranking Coreference Models》文章吗？方便提供源码吗？

NLG

请问下为什么没有机器创作之类的，AI写诗，写作

请问有中文多标签数据集吗

有關中文摘要

我看到了你們在這裡發佈的訊息，與把 Abstractive summarization 整合進 library 覺得非常好
https://chinesenlp.xyz/docs/text_summarization.html

一年前我在碩士期間研究了 Chinese summarization
這是我的 Paper

當初發現了 LCSTS 的資料集上有缺陷，在 training set 和 testing set 上有很大一部分的重複
聯繫 dataset 的作者，他後來發佈了 LCSTS2.0
但依然有重複的部分，我們提出了 LCSTS2.0-clean
且發表了 hybrid-word-character 的方法，在最原始版本的 LCSTS 資料集上 ROUGE score 達到快 60，但 LCSTS2.0-clean 上沒有這麼好，但也比其他的模型好。

這證明兩件事情

1. 資料集必須使用 LCSTS2.0，比較能公平的比較 model
2. hybrid-word-character 的方法確實是非常有用的

這是我的 paper
https://arxiv.org/abs/1802.09968

看到 DiDi 開源了非常多的項目，覺得很棒
希望能在這裡跟大家一起討論，謝謝

后面可以增加一个文本相似度的二分类任务？

请问是否可以识别性别

通过说话人的语言风格。