Yangqiu Song

Tsinghua University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Hongming Zhang

Bellevue Hospital Center

Tianqing Fang

Hong Kong University of Science and Technology

Weiqi Wang

Yangtze University

Changshui Zhang

Tsinghua University

Jiaxin Bai

University of Hong Kong

Dan Roth

University of Pennsylvania

Simon See

Nvidia (United States)

Xin Liu

Qingdao University of Science and Technology

Chunkit Chan

Hong Kong University of Science and Technology

Ginny Y. Wong

Nvidia (United States)

Cooperative Institutions

European Organization for Nuclear Research

571

Tsinghua University

384

University of Chinese Academy of Sciences

354

Centro Brasileiro de Pesquisas Físicas

333

Centre National de la Recherche Scientifique

293

Peking University

267

École Polytechnique Fédérale de Lausanne

242

Central China Normal University

201

Institute of High Energy Physics

197

Institut National de Physique Nucléaire et de Physique des Particules

195

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Entity Linking within a Social Media Platform: A Case Study on Yelp

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2018)

Hongliang Dai Yangqiu Song Liwei Qiu Rijia Liu

In this paper, we study a new entity linking problem where both the entity mentions and the target entities are within a same social media platform. Compared with traditional entity linking problems that link mentions to a knowledge base, this new problem have less information about the target entities. However, if we can successfully link mentions to entities within a social media platform, we can improve a lot of applications such as comparative study in business intelligence and opinion leader finding. To study this problem, we constructed a dataset called Yelp-EL, where the business mentions in Yelp reviews are linked to their corresponding businesses on the platform. We conducted comprehensive experiments and analysis on this dataset with a learning to rank model that takes different types of features as input, as well as a few state-of-the-art entity linking approaches. Our experimental results show that two types of features that are not available in traditional entity linking: social features and location features, can be very helpful for this task.

Entity linking

Rank (graph theory)

Sentiment Analysis

Base (topology)

10.18653/v1/d18-1227

Cite

Citations (4)

An Exploration of the Consumption Psychology of Young Chinese Online Game Consumers on Game Top-ups

Advances in Economics Management and Political Sciences (2024)

Yangqiu Song

With the rapid development of digital technology, China's online gaming industry has occupied an important position in the global landscape, and the number of young gamers has continued to increase. This study investigates the psychological factors that influence the game consumption behavior of young Chinese gamers, focusing on their motivations for consumption. By surveying 80 participants, the analysis found that key factors such as peer pressure, attractive recharge rewards, and promotions are important drivers of their consumption decisions. Research shows that these factors often encourage young users to make impulse purchases. In order to minimize the possible negative effects of excessive game-related spending, this paper proposes intervention strategies to promote responsible gaming behavior. The recommended measures include raising awareness of rational consumption, setting appropriate spending limits, and cultivating healthier gaming habits. These strategies aim to reduce adverse effects while achieving a more balanced gaming experience. The results provide meaningful insights into the consumption behavior of young Chinese gamers and provide practical recommendations for educators, policymakers, and parents to better support the well-being of young gamers.

Consumption

10.54254/2754-1169/2024.ga18960

Cite

Citations (0)

Does Summarization Help Stock Prediction? A News Impact Analysis

IEEE Intelligent Systems (2015)

Xiaodong Li Haoran Xie Yangqiu Song Shanfeng Zhu Qing Li

The authors study the problem of how news summarization can help stock price prediction, proposing a generic stock price prediction framework to enable the use of different external signals to predict stock prices. Experiments were conducted on five years of Hong Kong Stock Exchange data, with news reported by Finet; evaluations were performed at individual stock, sector index, and market index levels. The authors' results show that prediction based on news article summarization can effectively outperform prediction based on full-length articles on both validation and independent testing sets.

Stock (firearms)

Stock Market Prediction

Predictive modelling

10.1109/mis.2015.1

Cite

Citations (68)

Spectral Label Refinement for Noisy and Missing Text Labels

Proceedings of the AAAI Conference on Artificial Intelligence (2015)

Yangqiu Song Chenguang Wang Ming Zhang Hailong Sun Qiang Yang

With the recent growth of online content on the Web, there have been more user generated data with noisy and missing labels, e.g., social tags and voted labels from Amazon's Mechanical Turks. Most of machine learning methods, which require accurate label sets, could not be trusted when the label sets were yet unreliable. In this paper, we provide a text label refinement algorithm to adjust the labels for such noisy and missing labeled datasets. We assume that the labeled sets can be refined based on the labels with certain confidence, and the similarity between data being consistent with the labels. We propose a label smoothness ratio criterion to measure the smoothness of the labels and the consistency between labels and data. We demonstrate the effectiveness of the label refining algorithm on eight labeled document datasets, and validate that the results are useful for generating better labels.

Smoothness

Similarity (geometry)

Noisy data

Labeled data

10.1609/aaai.v29i1.9560

Cite

Citations (12)

Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model

Hongliang Dai Yangqiu Song Haixun Wang

Hongliang Dai, Yangqiu Song, Haixun Wang. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Computational linguistics

10.18653/v1/2021.acl-long.141

Cite

Citations (37)

Complex Hyperbolic Knowledge Graph Embeddings with Fast Fourier Transform

arXiv (Cornell University) (2022)

Huiru Xiao Xin Liu Yangqiu Song Ginny Y. Wong Simon See

The choice of geometric space for knowledge graph (KG) embeddings can have significant effects on the performance of KG completion tasks. The hyperbolic geometry has been shown to capture the hierarchical patterns due to its tree-like metrics, which addressed the limitations of the Euclidean embedding models. Recent explorations of the complex hyperbolic geometry further improved the hyperbolic embeddings for capturing a variety of hierarchical structures. However, the performance of the hyperbolic KG embedding models for non-transitive relations is still unpromising, while the complex hyperbolic embeddings do not deal with multi-relations. This paper aims to utilize the representation capacity of the complex hyperbolic geometry in multi-relational KG embeddings. To apply the geometric transformations which account for different relations and the attention mechanism in the complex hyperbolic space, we propose to use the fast Fourier transform (FFT) as the conversion between the real and complex hyperbolic space. Constructing the attention-based transformations in the complex space is very challenging, while the proposed Fourier transform-based complex hyperbolic approaches provide a simple and effective solution. Experimental results show that our methods outperform the baselines, including the Euclidean and the real hyperbolic embedding models.

Hyperbolic space

Hyperbolic tree

10.48550/arxiv.2211.03635

Cite

Citations (1)

Fine-grained Event Categorization with Heterogeneous Graph Convolutional Networks

arXiv (Cornell University) (2019)

Hao Peng Jianxin Li Qiran Gong Yangqiu Song Yuanxing Ning

Events are happening in real-world and real-time, which can be planned and organized occasions involving multiple people and objects. Social media platforms publish a lot of text messages containing public events with comprehensive topics. However, mining social events is challenging due to the heterogeneous event elements in texts and explicit and implicit social network structures. In this paper, we design an event meta-schema to characterize the semantic relatedness of social events and build an event-based heterogeneous information network (HIN) integrating information from external knowledge base, and propose a novel Pair-wise Popularity Graph Convolutional Network (PP-GCN) based fine-grained social event categorization model. We propose a Knowledgeable meta-paths Instances based social Event Similarity (KIES) between events and build a weighted adjacent matrix as input to the PP-GCN model. Comprehensive experiments on real data collections are conducted to compare various social event detection and clustering tasks. Experimental results demonstrate that our proposed framework outperforms other alternative social event categorization techniques.

Popularity

Publication

Schema (genetic algorithms)

Complex Event Processing

Social network (sociolinguistics)

10.48550/arxiv.1906.04580

Cite

Citations (7)

NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surrounding

arXiv (Cornell University) (2024)

Chunkit Chan Jay J. Cheng Yauwai Yim Zheye Deng Wei Fan

Large Language Models (LLMs) have sparked substantial interest and debate concerning their potential emergence of Theory of Mind (ToM) ability. Theory of mind evaluations currently focuses on testing models using machine-generated data or game settings prone to shortcuts and spurious correlations, which lacks evaluation of machine ToM ability in real-world human interaction scenarios. This poses a pressing demand to develop new real-world scenario benchmarks. We introduce NegotiationToM, a new benchmark designed to stress-test machine ToM in real-world negotiation surrounding covered multi-dimensional mental states (i.e., desires, beliefs, and intentions). Our benchmark builds upon the Belief-Desire-Intention (BDI) agent modeling theory and conducts the necessary empirical experiments to evaluate large language models. Our findings demonstrate that NegotiationToM is challenging for state-of-the-art LLMs, as they consistently perform significantly worse than humans, even when employing the chain-of-thought (CoT) method.

Benchmark (surveying)

Stress testing (software)

10.48550/arxiv.2404.13627

Cite

Citations (0)

Incorporating Context and External Knowledge for Pronoun Coreference Resolution

arXiv (Cornell University) (2019)

Hongming Zhang Yan Song Yangqiu Song

Linking pronominal expressions to the correct references requires, in many cases, better analysis of the contextual information and external knowledge. In this paper, we propose a two-layer model for pronoun coreference resolution that leverages both context and external knowledge, where a knowledge attention mechanism is designed to ensure the model leveraging the appropriate source of external knowledge based on different context. Experimental results demonstrate the validity and effectiveness of our model, where it outperforms state-of-the-art models by a large margin.

Coreference

Margin (machine learning)

10.48550/arxiv.1905.10238

Cite

Citations (3)

ASER: A Large-scale Eventuality Knowledge Graph

Hongming Zhang Xin Liu Haojie Pan Yangqiu Song Cane Wing-ki Leung

Understanding human’s language requires complex world knowledge. However, existing large-scale knowledge graphs mainly focus on knowledge about entities while ignoring knowledge about activities, states, or events, which are used to describe how entities or things act in the real world. To fill this gap, we develop ASER (activities, states, events, and their relations), a large-scale eventuality knowledge graph extracted from more than 11-billion-token unstructured textual data. ASER contains 15 relation types belonging to five categories, 194-million unique eventualities, and 64-million unique edges among them. Both intrinsic and extrinsic evaluations demonstrate the quality and effectiveness of ASER.

Knowledge graph

10.1145/3366423.3380107

Cite

Citations (115)