Min Zhang

Boost Phrase-level Polarity Labelling with Review-level Sentiment Classification

2015 · arXiv (Cornell University)

Sentiment analysis on user reviews helps to keep track of user reactions towards products, and make advices to users about what to buy. State-of-the-art review-level sentiment classification techniques could give pretty good precisions of above …

On the Construction of WeChat-based Platform of Great Courses

2016

MOOC and Microteaching, just like "a digital tsunami", are sweeping the entire education circle. Scholars have different opinions and each of them sticks to his or her argument. By comparing the Great Courses based on …

How Well Can WordNet Measure Privacy: A Comparative Study?

2017

Privacy is a fundamental issue in big data. Meanwhile, determining semantic relationships between words and phrases in privacy is required for effective privacy protection to the data that originates from a variety of sources, a …

A De-anonymization Attack for Social Network Graph Based on Structural and Node Feature Similarity

2018 · DEStech Transactions on Computer Science and Engineering

With the wide usage of Internet, social network has become an important carrier of information publishing and transmission in contemporary society. However, the anonymized information can still be de-anonymized because of the high frequency data-sharing …

Detecting Crowdturfing "Add to Favorites" Activities in Online Shopping

2018

"Add to Favorites" is a popular function in online shopping sites which helps users to make a record of potentially interesting items for future purchases. It is usually regarded as a type of explicit feedback …

A Two-Stage Model for User's Examination Behavior in Mobile Search

2018

With the rapid growth of mobile search, it is important to understand how users browse the mobile SERPs and allocate their limited attention to each result. To address this problem, we introduce a two-stage examination …

Attention-based Adaptive Model to Unify Warm and Cold Starts Recommendation

2018

Nowadays, recommender systems provide essential web services on the Internet. There are mainly two categories of traditional recommendation algorithms: Content-Based (CB) and Collaborative Filtering (CF). CF methods make recommendations mainly according to the historical feedback …

SEE: Syntax-Aware Entity Embedding for Neural Relation Extraction

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

Distant supervised relation extraction is an efficient approach to scale relation extraction to very large corpora, and has been widely used to find novel relational facts from plain text. Recent studies on neural relation extraction …

SUDA-Alibaba at MRP 2019: Graph-Based Models with BERT

2019

Yue Zhang, Wei Jiang, Qingrong Xia, Junjie Cao, Rui Wang, Zhenghua Li, Min Zhang. Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning. 2019.

Improving Neural Relation Extraction with Positive and Unlabeled Learning

2020 · Proceedings of the AAAI Conference on Artificial Intelligence

We present a novel approach to improve the performance of distant supervision relation extraction with Positive and Unlabeled (PU) Learning. This approach first applies reinforcement learning to decide whether a sentence is positive to a …

Token Drop mechanism for Neural Machine Translation

2020 · arXiv (Cornell University)

Neural machine translation with millions of parameters is vulnerable to unfamiliar inputs. We propose Token Drop to improve generalization and avoid overfitting for the NMT model. Similar to word dropout, whereas we replace dropped token …

Recommendation algorithm based on user attributes and tag preferences

2020 · Journal of Physics Conference Series

Abstract Aiming at the problem of sparse data and low recommendation accuracy of recommendation systems in a big data environment, a UT-CF algorithm that combines user attributes and tag preferences is proposed. The algorithm extracts …

Standing in Your Shoes: External Assessments for Personalized Recommender Systems

2021

The evaluation of recommender systems relies on user preference data, which is difficult to acquire directly because of its subjective nature. Current recommender systems widely utilize users' historical interactions as implicit or explicit feedback, but …

Global or Local: Constructing Personalized Click Models for Web Search

2022 · Proceedings of the ACM Web Conference 2022

Click models are widely used for user simulation, relevance inference, and evaluation in Web search. Most existing click models implicitly assume that users’ relevance judgment and behavior patterns are homogeneous. However, previous studies have shown …

BLISS: Robust Sequence-to-Sequence Learning via Self-Supervised Input Representation

2022 · arXiv (Cornell University)

Data augmentations (DA) are the cores to achieving robust sequence-to-sequence learning on various natural language processing (NLP) tasks. However, most of the DA approaches force the decoder to make predictions conditioned on the perturbed input …

Cloud Resource Scheduling Algorithm Based on Combination Weight

2022 · 2022 IEEE 10th Joint International Information Technology and Artificial Intelligence Conference (ITAIC)

The default scheduling algorithm in the cloud environment only considers the two performance indicators of CPU and memory, and uses a unified weight to calculate the candidate node score, which cannot meet the needs of …

RotoGBML: Towards Out-of-Distribution Generalization for Gradient-Based Meta-Learning

2023 · arXiv (Cornell University)

Gradient-based meta-learning (GBML) algorithms are able to fast adapt to new tasks by transferring the learned meta-knowledge, while assuming that all tasks come from the same distribution (in-distribution, ID). However, in the real world, they …

ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translation

2022

Transfer learning is a simple and powerful method that can be used to boost model performance of low-resource neural machine translation (NMT). Existing transfer learning methods for NMT are static, which simply transfer knowledge from …

Artifact for Marabou 2.0: A Versatile Formal Analyzer of Neural Networks

2024 · arXiv (Cornell University)

This paper serves as a comprehensive system description of version 2.0 of the Marabou framework for formal analysis of neural networks. We discuss the tool's architectural design and highlight the major features and components introduced …

When Large Language Models Meet Vector Databases: A Survey

2024 · arXiv (Cornell University)

This survey explores the synergistic potential of Large Language Models (LLMs) and Vector Databases (VecDBs), a burgeoning but rapidly evolving research area. With the proliferation of LLMs comes a host of challenges, including hallucinations, outdated …

Pareto Graph Self-Supervised Learning

2024

In this paper, we study the problem of finding proper tradeoff for graph self-supervised learning. Recently, various self-supervised auxiliary tasks have been proposed to accelerate representation learning in Graph Neural Networks (GNNs). However, existing graph …

Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Model

2024 · arXiv (Cornell University)

Large language models (LLMs) have showcased impressive multilingual machine translation ability. However, unlike encoder-decoder style models, decoder-only LLMs lack an explicit alignment between source and target contexts. Analyzing contribution scores during generation processes revealed that …

Development of Smart Operation and Maintenance Platform for Distributed Large-scale Battery Energy Storage Stations Based on Cloud Edge Collaboration

2024

With the continuous growth of the installed capacity of battery storage power stations and the expansion of single station scale, the operation and maintenance level has become the key to reducing costs, increasing efficiency, and …

Marabou 2.0: A Versatile Formal Analyzer of Neural Networks

2024 · Lecture notes in computer science

Abstract This paper serves as a comprehensive system description of version 2.0 of the Marabou framework for formal analysis of neural networks. We discuss the tool’s architectural design and highlight the major features and components …

Research on the Use of Intangible Cultural Heritage (ICH) Music in Primary and Secondary School Music Education in the Era of Artificial Intelligence

2024 · Journal of Education and Educational Research

Recently, the General Office of the Ministry of Education issued the Notice on Strengthening Artificial Intelligence Education in Primary and Secondary Schools, which will basically popularize artificial intelligence education in primary and secondary schools before …

A frequency attention-embedded network for polyp segmentation

2025 · Scientific Reports

Gastrointestinal polyps are observed and treated under endoscopy, so there presents significant challenges to advance endoscopy imaging segmentation of polyps. Current methodologies often falter in distinguishing complex polyp structures within diverse (mucosal) tissue environments. In …

UPPR+: Scaling Uncertain Personalised PageRank Computation on Billion-Sized Graphs with Mutually Exclusive Edges

2025

While Personalised PageRank (PPR) is widely used for ranking nodes in certain graphs, research on PPR for uncertain graphs remains limited. Real-world graphs often exhibit uncertainty in some edges with interdependent probabilities. The best-of-breed work …

AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration

2025

Multi-agent systems (MAS) based on large language models (LLMs) have demonstrated significant potential in collaborative problemsolving.However, they still face substantial challenges of low communication efficiency and suboptimal task performance, making the careful design of the …

Report on the 3rd Workshop on NeuroPhysiological Approaches for Interactive Information Retrieval (NeuroPhysIIR 2025) at SIGIR CHIIR 2025

2025 · ACM SIGIR Forum

The International Workshop on NeuroPhysiological Approaches for Interactive Information Retrieval (NeuroPhysIIR'25), co-located with ACM SIGIR CHIIR 2025 in Naarm/Melbourne, Australia, included 19 participants who discussed 12 statements addressing open challenges in neurophysiological interactive IR. The …

Understanding Internal Representations of Recommendation Models with Sparse Autoencoders

2026 · ACM Transactions on Information Systems

Recommendation model interpretation aims to reveal the relationships between inputs, model internal representations, and outputs to enhance the transparency, interpretability, and trustworthiness of recommendation systems. However, the inherent complexity and opacity of deep learning models …

PLaST: Towards Paralinguistic-aware Speech Translation

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

Speech translation (ST) aims to translate speech from a source language into text in the target language. Naturally, speech signals contain paralinguistic cues beyond linguistic content, which could influence or even alter the interpretation of …

Daily-Aware Personalized Recommendation based on Feature-Level Time Series Analysis

2015

The frequently changing user preferences and/or item profiles have put essential importance on the dynamic modeling of users and items in personalized recommender systems. However, due to the insufficiency of per user/item records when splitting …

Fairness-Aware Group Recommendation with Pareto-Efficiency

2017

Group recommendation has attracted significant research efforts for its importance in benefiting a group of users. This paper investigates the Group Recommendation problem from a novel aspect, which tries to maximize the satisfaction of each …

How good your recommender system is? A survey on evaluations in recommendation

2017 · International Journal of Machine Learning and Cybernetics

Recommender Systems have become a very useful tool for a large variety of domains. Researchers have been attempting to improve their algorithms in order to issue better predictions to the users. However, one of the …

Neural Attentional Rating Regression with Review-level Explanations

2018

Reviews information is dominant for users to make online purchasing decisions in e-commerces. However, the usefulness of reviews is varied. We argue that less-useful reviews hurt model's performance, and are also less meaningful for user's …

Between Clicks and Satisfaction

2018

Click signal has been widely used for designing and evaluating interactive information systems, which is taken as the indicator of user preference. However, click signal does not capture post-click user experience. Very commonly, the user …

Distantly Supervised NER with Partial Annotation Learning and Reinforcement Learning

2018 · International Conference on Computational Linguistics

A bottleneck problem with Chinese named entity recognition (NER) in new domains is the lack of annotated data. One solution is to utilize the method of distant supervision, which has been widely used in relation …

Social Attentional Memory Network

2019

Social connections are known to be helpful for modeling users' potential preferences and improving the performance of recommender systems. However, in social-aware recommendations, there are two issues which influence the inference of users' preferences, and …

Jointly Learning Explainable Rules for Recommendation with Knowledge Graph

2019

Explainability and effectiveness are two key aspects for building recommender systems. Prior efforts mostly focus on incorporating side information to achieve better recommendation performance. However, these methods have some weaknesses: (1) prediction of neural network-based …

An Efficient Adaptive Transfer Neural Network for Social-aware Recommendation

2019

Many previous studies attempt to utilize information from other domains to achieve better performance of recommendation. Recently, social information has been shown effective in improving recommendation results with transfer learning frameworks, and the transfer part …

Variational Neural Machine Translation

2016

Models of neural machine translation are often from a discriminative family of encoderdecoders that learn a conditional distribution of a target sentence given a source sentence. In this paper, we propose a variational model to …

Modeling Source Syntax for Neural Machine Translation

2017

Even though a linguistics-free sequence to sequence model in neural machine translation (NMT) has certain capability of implicitly learning syntactic information of source sentences, this paper shows that source syntax can be explicitly incorporated into …

Efficient Neural Matrix Factorization without Sampling for Recommendation

2020 · ACM Transactions on Information Systems

Recommendation systems play a vital role to keep users engaged with personalized contents in modern online platforms. Recently, deep learning has revolutionized many research fields and there is a surge of interest in applying it …

A Survey on the Fairness of Recommender Systems

2022 · ACM Transactions on Information Systems

Recommender systems are an essential tool to relieve the information overload challenge and play an important role in people’s daily lives. Since recommendations involve allocations of social resources (e.g., job recommendation), an important issue is …