Dongsheng Li

ERMMA: Expected Risk Minimization for Matrix Approximation-based Recommender Systems

2017 · Proceedings of the AAAI Conference on Artificial Intelligence

Matrix approximation (MA) is one of the most popular techniques in today's recommender systems. In most MA-based recommender systems, the problem of risk minimization should be defined, and how to achieve minimum expected risk in …

Read + Verify: Machine Reading Comprehension with Unanswerable Questions

2018 · arXiv (Cornell University)

Machine reading comprehension with unanswerable questions aims to abstain from answering when no answer can be inferred. In addition to extract answers, previous works usually predict an additional "no-answer" probability to detect unanswerable cases. However, …

Collaborative Filtering with Noisy Ratings

2019 · Society for Industrial and Applied Mathematics eBooks

User ratings on items are noisy in real-world recommender systems, which raises challenges to matrix approximation (MA)-based collaborative filtering (CF) algorithms — the learned models will be easily biased to the noisy training data and …

Non-Ergodic Convergence Analysis of Heavy-Ball Algorithms

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

In this paper, we revisit the convergence of the Heavy-ball method, and present improved convergence complexity results in the convex setting. We provide the first non-ergodic O(1/k) rate result of the Heavy-ball algorithm with constant …

How Powerful is Graph Convolution for Recommendation?

2021

Graph convolutional networks (GCNs) have recently enabled a popular class of algorithms for collaborative filtering (CF). Nevertheless, the theoretical underpinnings of their empirical successes remain elusive. In this paper, we endeavor to obtain a better …

DiffusionNER: Boundary Diffusion for Named Entity Recognition

2023 · arXiv (Cornell University)

In this paper, we propose DiffusionNER, which formulates the named entity recognition task as a boundary-denoising diffusion process and thus generates named entities from noisy spans. During training, DiffusionNER gradually adds noises to the golden …

Span extraction and contrastive learning for coreference resolution

2022

Coreference resolution is a primary task in natural language processing (NLP), designed to automatically identifyand classify noun phrases or pronouns that represent thesame mention. Most of the recent coreference resolution models extraction or cluster mentions. …

Is Risk-Sensitive Reinforcement Learning Properly Resolved?

2023 · arXiv (Cornell University)

Due to the nature of risk management in learning applicable policies, risk-sensitive reinforcement learning (RSRL) has been realized as an important direction. RSRL is usually achieved by learning risk-sensitive objectives characterized by various risk measures, …

Exploring Pre-trained Language Models for Event Extraction and Generation

2019

Traditional approaches to the task of ACE event extraction usually depend on manually annotated data, which is often laborious to create and limited in size. Therefore, in addition to the difficulty of event extraction itself, …

Attention-Guided Answer Distillation for Machine Reading Comprehension

2018

Despite that current reading comprehension systems have achieved significant advancements, their promising performances are often obtained at the cost of making an ensemble of numerous models. Besides, existing approaches are also vulnerable to adversarial attacks. …

Read + Verify: Machine Reading Comprehension with Unanswerable Questions

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

Machine reading comprehension with unanswerable questions aims to abstain from answering when no answer can be inferred. In addition to extract answers, previous works usually predict an additional “no-answer” probability to detect unanswerable cases. However, …