Share your thoughts on HanLP. Discussions are welcomed on our forum, while bug reports and feature requests are reserved for GitHub issues.

SOTA Language Models, distillation and application.

Task/Conversational QA, KBQA/DocQA, MRC, Multi-hop Reasoning, etc.

《自然语言处理入门》是一本务实的NLP入门书，助你零起点上手自然语言处理。

Discussion about bbs.hankcs.com itself, the organization of this forum, how it works, and how we can improve this site.

Share corpora and datasets. Discuss corpus annotation, preprocessing and application.

Machine Learning theories, statistical learning methods.

Learning representations for graph-structured data.

Knowledge Graph representation, multi-hop reasoning, etc.

Tagging based tasks like Named Entity Recognition, chunking, etc.

We accomodate AMR researchers in this category. Discussions on AMR corpora, parsing algorithm, papers and applications are welcomed.

Topics falling outside of current categories. Jokes, rumors etc.

Summarization is the task of producing a shorter summary of documents that preserves most important or relevant information within the original content.

Novel parsing algorithms, SOTA decoders, intermediate grammar, treebanks construction
and application in dialog domain.

Semantic textual similarity deals with determining how similar two pieces of texts are.

Machine translation is the task of translating a sentence in a source language to a different target language.

Text style transfer aims to change the style of the input text to the target style while preserving its content.