Min Yang

Activity Recommendation with Partners

2017 · ACM Transactions on the Web

Recommending social activities , such as watching movies or having dinner, is a common function found in social networks or e-commerce sites. Besides certain websites which manage activity-related locations (e.g., foursquare.com), many items on product …

Investigating Deep Reinforcement Learning Techniques in Personalized Dialogue Generation

2018 · Society for Industrial and Applied Mathematics eBooks

In this paper, we propose a personalized dialogue generation system, which combines reinforcement learning techniques with an attention-based hierarchical recurrent encoderdecoder model. Firstly, we incorporate user-specific information into the decoder to capture user's background information …

Improving automatic source code summarization via deep reinforcement learning

2018

Code summarization provides a high level natural language description of the function performed by code, as it can benefit the software maintenance, code categorization and retrieval. To the best of our knowledge, most state-of-the-art approaches …

Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications

2019 · arXiv (Cornell University)

Obstacles hindering the development of capsule networks for challenging NLP applications include poor scalability to large output spaces and less reliable routing processes. In this paper, we introduce: 1) an agreement score to evaluate the …

Improving the Robustness of Wasserstein Embedding by Adversarial PAC-Bayesian Learning

2020 · Proceedings of the AAAI Conference on Artificial Intelligence

Node embedding is a crucial task in graph analysis. Recently, several methods are proposed to embed a node as a distribution rather than a vector to capture more information. Although these methods achieved noticeable improvements, …

Bridging Hierarchical and Sequential Context Modeling for Question-driven Extractive Answer Summarization

2020

Non-factoid question answering (QA) is one of the most extensive yet challenging application and research areas of retrieval-based question answering. In particular, answers to non-factoid questions can often be too lengthy and redundant to comprehend, …

An Effective Hybrid Learning Model for Real-Time Event Summarization

2020 · IEEE Transactions on Neural Networks and Learning Systems

Real-time event summarization (RES) aims at extracting a handful of document updates from an overwhelming document stream as the real-time event summary that tracks and summarizes the evolving event of interest. It has been attracting …

Weak Links in Authentication Chains: A Large-scale Analysis of Email Sender Spoofing Attacks

2020 · arXiv (Cornell University)

As a fundamental communicative service, email is playing an important role in both individual and corporate communications, which also makes it one of the most frequently attack vectors. An email's authenticity is based on an …

Collaborative filtering recommendation algorithm based on KNN and Xgboost hybrid

2021 · Journal of Physics Conference Series

Abstract In the traditional collaborative filtering recommendation algorithm, it is easy to fall into the dilemma of local optimization due to single classification, which affects the recommendation effect of the algorithm. A hybrid collaborative filtering …

Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment Classification

2021

Lifelong learning capabilities are crucial for sentiment classifiers to process continuous streams of opinioned information on the Web. However, performing lifelong learning is non-trivial for deep neural networks as continually training of incrementally available information …

MaSS: Model-agnostic, Semantic and Stealthy Data Poisoning Attack on Knowledge Graph Embedding

2023

Open-source knowledge graphs are attracting increasing attention. Nevertheless, the openness also raises the concern of data poisoning attacks, that is, the attacker could submit malicious facts to bias the prediction of knowledge graph embedding (KGE) …

Type-Enhanced Ensemble Triple Representation via Triple-Aware Attention for Cross-Lingual Entity Alignment

2024 · IEICE Transactions on Information and Systems

Entity alignment (EA) is a crucial task for integrating cross-lingual and cross-domain knowledge graphs (KGs), which aims to discover entities referring to the same real-world object from different KGs. Most existing embedding-based methods generate aligning …

You Can't Eat Your Cake and Have It Too: The Performance Degradation of LLMs with Jailbreak Defense

2025 · arXiv (Cornell University)

With the rise of generative large language models (LLMs) like LLaMA and ChatGPT, these models have significantly transformed daily life and work by providing advanced insights. However, as jailbreak attacks continue to circumvent built-in safety …

Quantification of Large Language Model Distillation

2025 · arXiv (Cornell University)

Model distillation is a fundamental technique in building large language models (LLMs), transferring knowledge from a teacher model to a student model. However, distillation can lead to model homogenization, reducing diversity among models and impairing …

Generative Adversarial Network for Abstractive Text Summarization

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

In this paper, we propose an adversarial process for abstractive text summarization, in which we simultaneously train a generative model G and a discriminative model D. In particular, we build the generator G as an …