Ruosong Yang

Ruosong Yang

Auto-generated profile, based on publicly available information

Ruosong Yang

China Mobile (Hong Kong) Innovation and Research Institute Hong Kong, Hong Kong

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
11 March 2022 in Information Processing & Management
Verified
Journal Article
Closed access
SLShuaiqi Liu
Shuaiqi Liu
JCJiannong Cao
Jiannong Cao
RYRuosong Yang
Ruosong Yang
ZWZhiyuan Wen
Zhiyuan Wen

3 June 2024 in Information Processing & Management
Verified
Journal Article
Closed access
SLShuaiqi Liu
Shuaiqi Liu
JCJiannong Cao
Jiannong Cao
YLYicong Li
Yicong Li
RYRuosong Yang
Ruosong Yang
ZWZhiyuan Wen
Zhiyuan Wen

13 May 2024 in ACM Transactions on Information Systems
Verified
Journal Article
Open access
ZWZhiyuan Wen
Zhiyuan Wen
JCJiannong Cao
Jiannong Cao
Jiaxing SHENJiaxing SHEN
Jiaxing SHEN
RYRuosong Yang
Ruosong Yang
SLShuaiqi Liu
Shuaiqi Liu
MSMaosong Sun
Maosong Sun
Generating appropriate emotions for responses is essential for dialogue systems to provide human-like interaction in various application scenarios. Most previous dialogue systems tried to achieve this goal by learning empathetic manners from anonymous conversational data. However, emotional responses generated by those methods may be inconsistent, which will decrease user engagement and service quality. Psychological findings suggest that the emotional expressions of humans are rooted in personality traits. Therefore, we propose a new task, Personality-affected Emotion Generation, to generate emotion based on the personality given to the dialogue system and further investigate a solution through the personality-affected mood transition. Specifically, we first construct a daily dialogue dataset, Personality EmotionLines Dataset ( PELD ), with emotion and personality annotations. Subsequently, we analyze the challenges in this task, i.e., (1) heterogeneously integrating personality and emotional factors and (2) extracting multi-granularity emotional information in the dialogue context. Finally, we propose to model the personality as the transition weight by simulating the mood transition process in the dialogue system and solve the challenges above. We conduct extensive experiments on PELD for evaluation. Results suggest that by adopting our method, the emotion generation performance is improved by 13% in macro-F1 and 5% in weighted-F1 from the BERT-base model.

1 January 2021
Verified
Conference Paper
Open access
PDF file
ZWZhiyuan Wen
Zhiyuan Wen
JCJiannong Cao
Jiannong Cao
RYRuosong Yang
Ruosong Yang
SLShuaiqi Liu
Shuaiqi Liu
Jiaxing SHENJiaxing SHEN
Jiaxing SHEN
Zhiyuan Wen, Jiannong Cao, Ruosong Yang, Shuaiqi Liu, Jiaxing Shen. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. 2021.

13 October 2023 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
SLShuaiqi Liu
Shuaiqi Liu
JCJiannong Cao
Jiannong Cao
ZDZhongfen Deng
Zhongfen Deng
WZWenting Zhao
Wenting Zhao
RYRuosong Yang
Ruosong Yang
PYPhilip S. Yu
Philip S. Yu
Abstractive summarization aims to generate a concise summary covering the input document's salient information. Within a report document, the salient information can be scattered in the textual and non-textual content. However, existing document summarization datasets and methods usually focus on the text and filter out the non-textual content. Missing tabular data can limit produced summaries’ informativeness, especially when summaries require covering quantitative descriptions of critical metrics in tables. Existing datasets and methods cannot meet the requirements of summarizing long text and dozens of tables in each report document. To deal with the scarcity of available datasets, we propose FINDSum, the first large-scale dataset for long text and multi-table summarization. Built on 21,125 annual reports from 3,794 companies, FINDSum has two subsets for summarizing each company's results of operations and liquidity. Besides, we present four types of summarization methods to jointly consider text and table content when summarizing reports. Additionally, we propose a set of evaluation metrics to assess the usage of numerical information in produced summaries. Our summarization methods significantly outperform advanced baselines, which verifies the necessity of incorporating textual and tabular data when summarizing report documents. We also conduct extensive comparative experiments to identify vital model components and configurations that can improve summarization results.

1 June 2018
Verified
Conference Paper
Closed access
HWHanqing Wu
Hanqing Wu
JCJiannong Cao
Jiannong Cao
Shan JiangShan Jiang
Shan Jiang
RYRuosong Yang
Ruosong Yang
YYYanni Yang
Yanni Yang
JHJianfei Hey
Jianfei Hey
Nowadays is the big data era. A large amount of data are generated which can be valuable for business, healthcare, transportation, etc. To promote the dissemination of the valuable data, researchers have been trying to design and develop data sharing platforms. However, the existing platforms fail to address at least one of the three issues: trustworthiness, data heterogeneity, and authenticability. To this end, we propose TSAR, a fully-distributed Trustless data ShARing platform. In detail, we architect TSAR on Blockchain to remove the dependency on reliable third parties, which realizes the trustworthiness. Moreover, we propose a general data schema to represent raw data, which handles the problem of data heterogeneity. Finally, we record the data transaction as well as user-group information on Blockchain to achieve authenticability. To demonstrate the practicability and effectiveness of TSAR, we implement it in a minimal-viable-product fashion and evaluate the performance in terms of throughput and response time.