Ruosong Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ruosong Yang has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Jiannong Cao
The Hong Kong Polytechnic University
8 shared publications - Zhiyuan Wen
Hong Kong Polytechnic University, Hong Kong, China
7 shared publications - Shuaiqi Liu
Alibaba Group, China
5 shared publications - Jiaxing Shen
Lingnan University
4 shared publications Jiannong Cao
2 shared publications- Bo Yuan
JIUTIAN Research, China Mobile, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13658-13666
FOCAL: Filtered On-device Continuous Activity Logging for Efficient Personal Desktop Summarization
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13658-13666
Open AccessFOCAL: Filtered On-device Continuous Activity Logging for Efficient Personal Desktop Summarization
- Open Access
- 4 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 85-92
FedHO: Memory-Efficient Federated Fine-Tuning for Large Models via Hybrid Gradient Computation
- 4 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 85-92
Open AccessFedHO: Memory-Efficient Federated Fine-Tuning for Large Models via Hybrid Gradient Computation
- Top Cited Papers
- 3 June 2024
- Published by Elsevier in Information Processing & Management
- Vol. 61 (5)
Low-resource court judgment summarization for common law systems
- 3 June 2024
- Published by Elsevier in Information Processing & Management
- Vol. 61 (5)
Top Cited PapersLow-resource court judgment summarization for common law systems
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (5) , 1-27
Personality-affected Emotion Generation in Dialog Systems
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.
- 13 May 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (5) , 1-27
Open AccessPersonality-affected Emotion Generation in Dialog Systems
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.
- 13 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (6) , 2572-2586
Neural Abstractive Summarization for Long Text and Multiple Tables
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.
- 13 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (6) , 2572-2586
Neural Abstractive Summarization for Long Text and Multiple Tables
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.
- 11 March 2022
- Published by Elsevier in Information Processing & Management
- Vol. 59 (3)
Key phrase aware transformer for abstractive summarization
- 11 March 2022
- Published by Elsevier in Information Processing & Management
- Vol. 59 (3)
Key phrase aware transformer for abstractive summarization
- 10 March 2022
- Published by Springer Nature in World Wide Web
- Vol. 25 (3) , 1197-1221
Automated post scoring: evaluating posts with topics and quoted posts in online forum
Online forumpost evaluationis an effective way for instructors to assess students’ knowledge understanding and writing mechanics. Manually evaluating massive posts costs a lot of time. Automatically grading online posts could significantly alleviate instructors’ burden. Similar text assessment tasks like Automated Text Scoring evaluate the writing quality of independent texts or relevance between text and prompt. And Automatic Short Answer Grading measures the semantic matching of short answers according to given problems and correct answers. Different from existing tasks, we propose a novel task, Automated Post Scoring (APS), which grades all online discussion posts in each thread of each student with given topics and quoted posts. APS evaluates not only the writing quality of posts automatically but also the relevance to topics. To measure the relevance, we model the semantic consistency between posts and topics. Supporting arguments are also extracted from quoted posts to enhance posts evaluation. Specifically, we propose a mixture model including a hierarchical text model to measure the writing quality, a semantic matching model to model topic relevance, and a semantic representation model to integrate quoted posts. We also construct a new dataset called Online Discussion Dataset containing 2,542 online posts from 694 students of a social science course. The proposed models are evaluated on the dataset with correlation and residual based evaluation metrics. Compared with measuring posts alone, experimental results demonstrate that incorporating topics and quoted posts could improve the performance of APS by a large margin, more than 9 percent on QWK.
- 10 March 2022
- Published by Springer Nature in World Wide Web
- Vol. 25 (3) , 1197-1221
Automated post scoring: evaluating posts with topics and quoted posts in online forum
Online forumpost evaluationis an effective way for instructors to assess students’ knowledge understanding and writing mechanics. Manually evaluating massive posts costs a lot of time. Automatically grading online posts could significantly alleviate instructors’ burden. Similar text assessment tasks like Automated Text Scoring evaluate the writing quality of independent texts or relevance between text and prompt. And Automatic Short Answer Grading measures the semantic matching of short answers according to given problems and correct answers. Different from existing tasks, we propose a novel task, Automated Post Scoring (APS), which grades all online discussion posts in each thread of each student with given topics and quoted posts. APS evaluates not only the writing quality of posts automatically but also the relevance to topics. To measure the relevance, we model the semantic consistency between posts and topics. Supporting arguments are also extracted from quoted posts to enhance posts evaluation. Specifically, we propose a mixture model including a hierarchical text model to measure the writing quality, a semantic matching model to model topic relevance, and a semantic representation model to integrate quoted posts. We also construct a new dataset called Online Discussion Dataset containing 2,542 online posts from 694 students of a social science course. The proposed models are evaluated on the dataset with correlation and residual based evaluation metrics. Compared with measuring posts alone, experimental results demonstrate that incorporating topics and quoted posts could improve the performance of APS by a large margin, more than 9 percent on QWK.
- Open Access
- 1 January 2021
- Published by Association for Computational Linguistics (ACL)
- p. 5010-5020
Automatically Select Emotion for Response via Personality-affected Emotion Transition
Zhiyuan Wen, Jiannong Cao, Ruosong Yang, Shuaiqi Liu, Jiaxing Shen. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. 2021.
- 1 January 2021
- Published by Association for Computational Linguistics (ACL)
- p. 5010-5020
Open AccessAutomatically Select Emotion for Response via Personality-affected Emotion Transition
Zhiyuan Wen, Jiannong Cao, Ruosong Yang, Shuaiqi Liu, Jiaxing Shen. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. 2021.
- 18 July 2020
- Published by Springer Nature
- p. 15-24
Learning Analytics Based on Multilayer Behavior Fusion
- 18 July 2020
- Published by Springer Nature
- p. 15-24
Learning Analytics Based on Multilayer Behavior Fusion
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 350-355
TSAR: A Fully-Distributed Trustless Data ShARing Platform
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.
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 350-355
TSAR: A Fully-Distributed Trustless Data ShARing Platform
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.