Shuangyong Song

Shuangyong Song

Auto-generated profile, based on publicly available information

Shuangyong Song

Institute of Artificial Intelligence (TeleAI), China Telecom Corp Ltd, Beijing, China

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2015
Verified
Conference Paper
Closed access
SSShuangyong Song
Shuangyong Song
YMYao Meng
Yao Meng
ZZZhongguang Zheng
Zhongguang Zheng

18 July 2023
Verified
Conference Paper
Open access
KOKai Ouyang
Kai Ouyang
XXXianghong Xu
Xianghong Xu
MCMiaoxin Chen
Miaoxin Chen
ZXZuotong Xie
Zuotong Xie
Hai-Tao ZhengHai-Tao Zheng
Hai-Tao Zheng
YZYu Zhao
Yu Zhao

3 April 2020 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
RYRiheng Yao
Riheng Yao
SSShuangyong Song
Shuangyong Song
QLQiudan Li
Qiudan Li
Chao WangChao Wang
Chao Wang
HCHuan Chen
Huan Chen
DZDaniel Dajun Zeng
Daniel Dajun Zeng
This paper aims to predict user satisfaction for customer service chatbot in session level, which is of great practical significance yet rather untouched. It requires to explore the relationship between questions and answers across different rounds of interactions, and handle user bias. We propose an approach to model multi-round conversations within one session and take user information into account. Experimental results on a dataset from a real-world industrial customer service chatbot Alime demonstrate the good performance of our proposed model.

8 April 2025 in Knowledge-Based Systems
Verified
Journal Article
Closed access
HSHaoxiang Su
Haoxiang Su
HXHongyan Xie
Hongyan Xie
JSJie Shi
Jie Shi
DWDi Wu
Di Wu
LJLiting Jiang
Liting Jiang
SSShuangyong Song
Shuangyong Song

28 October 2024
Verified
Conference Paper
Open access
DZDeji Zhao
Deji Zhao
DHDong Hong Han
Dong Hong Han
YYYe Yuan
Ye Yuan
Bo NingBo Ning
Bo Ning
MLMengxiang Li
Mengxiang Li
SSShuangyong Song
Shuangyong Song
Open-domain multi-modal dialogue system heavily relies on visual information to generate contextually relevant responses. The existing open-domain multi-modal dialog generation methods ignore the complementary relationship between multiple modalities, and are difficult to integrate with LLMs. To tackle these challenges, we introduce AutoGraph, an innovative method for constructing visual context graphs automatically. We aim to structure complex information and seamlessly integrate it with large language models (LLMs), aligning information from multiple modalities at both semantic and structural levels. Specifically, we fully connect the text graphs and scene graphs, and then trim unnecessary edges via LLMs to automatically construct a visual context graph. Next, we design several graph sampling grammar for the first time to convert graph structures into sequence which is suitable for LLMs. Finally, we propose a two-stage fine-tuning strategy to allow LLMs to understand graph sampling grammar and generate responses. We validate our proposed method on text-based LLMs, and visual-based LLMs, respectively. Experimental results show that our proposed method achieves state-of-the-art performance on multiple public datasets.

27 July 2026 in Neurocomputing
Verified
Journal Article
Closed access
HXHongyan Xie
Hongyan Xie
YBYikun Ban
Yikun Ban
RFRuiyu Fang
Ruiyu Fang
DWDi Wu
Di Wu
ZHZixuan Huang
Zixuan Huang
SSShuangyong Song
Shuangyong Song