{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/eva-an-open-domain-chinese-dialogue-system","title":"EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training","arxiv_id":"2108.01547","date":"2021-08-03","proceeding":null,"authors":["Hao Zhou","Pei Ke","Zheng Zhang","Yuxian Gu","Yinhe Zheng","Chujie Zheng","Yida Wang","Chen Henry Wu","Hao Sun","Xiaocong Yang","Bosi Wen","Xiaoyan Zhu","Minlie Huang","Jie Tang"],"abstract":"Although pre-trained language models have remarkably enhanced the generation ability of dialogue systems, open-domain Chinese dialogue systems are still limited by the dialogue data and the model size compared with English ones. In this paper, we propose EVA, a Chinese dialogue system that contains the largest Chinese pre-trained dialogue model with 2.8B parameters. To build this model, we collect the largest Chinese dialogue dataset named WDC-Dialogue from various public social media. This dataset contains 1.4B context-response pairs and is used as the pre-training corpus of EVA. Extensive experiments on automatic and human evaluation show that EVA outperforms other Chinese pre-trained dialogue models especially in the multi-turn interaction of human-bot conversations.","url_abs":"https://arxiv.org/abs/2108.01547v1","url_pdf":"https://arxiv.org/pdf/2108.01547v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"eva-an-open-domain-chinese-dialogue-system","repo_url":"https://github.com/thu-coai/EVA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"eva-an-open-domain-chinese-dialogue-system","repo_url":"https://github.com/openbmb/bminf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"wdc-dialogue","name":"WDC-Dialogue","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2108.01547","atlas_url":"https://app.syntology.ai/?focus=2108.01547","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}