AlibabaResearch/DAMO-ConvAI

DAMO-ConvAI: The official repository which contains the codebase for Alibaba DAMO Conversational AI.

What it solves

DAMO ConvAI provides a centralized codebase for Alibaba DAMO Academy's research into conversational AI, focusing on improving how machines understand and interact with users through dialogue systems.

How it works

The repository serves as the official codebase for various conversational AI projects and research papers, including work on Text-to-SQL (such as S²SQL and R²SQL) and dialogue state tracking (DSTC11).

Who it’s for

Researchers and developers interested in advanced conversational AI, specifically those looking to implement or reproduce the results of Alibaba DAMO Academy's published research papers.

Highlights

  • High performance in Text-to-SQL tasks, achieving top rankings on the Spider, SparC, and CoSQL leaderboards.
  • Extensive academic validation with numerous papers accepted at top AI conferences like ACL, EMNLP, and NeurIPS.
  • Focuses on conversational AI research including dialogue state tracking and structured data interaction.

Related

  • Project
    enoch3712/ExtractThinker

    A Python library that converts unstructured documents into validated Pydantic objects using LLMs and customizable document loaders.

  • Project
    actionbook/actionbook

    An AI browser agent that uses a Chrome extension and MCP connector to operate websites concurrently and access data behind logins to deliver finished work.

  • Project
    apache/opennlp

    Apache OpenNLP is a Java library offering classic NLP tools—tokenization, POS tagging, NER, parsing, etc.—via a modular, Maven‑based architecture and both API and CLI interfaces.

  • Project
    Joooook/12306-mcp

    An MCP-based server that allows Large Language Models to search for 12306 Chinese railway ticket information, including transfers and stop-overs.