Jie Tang

Entity Matching across Heterogeneous Sources

2015

Given an entity in a source domain, finding its matched entities from another (target) domain is an important task in many applications. Traditionally, the problem was usually addressed by first extracting major keywords corresponding to …

LEAP

2017

Managing patients with complex multimorbidity has long been recognized as a difficult problem due to complex disease and medication dependencies and the potential risk of adverse drug interactions. Existing work either uses complicated rule-based protocols …

Weakly Learning to Match Experts in Online Community

2016 · arXiv (Cornell University)

In online question-and-answer (QA) websites like Quora, one central issue is to find (invite) users who are able to provide answers to a given question and at the same time would be unlikely to say …

Course Concept Extraction in MOOC via Explicit/Implicit Representation

2018

Massive Open Online Courses(MOOCs) provide convenient access to knowledge for learners all over the world. Concept Extraction is a basic requirement in MOOCs. However, textual content in MOOCs, such as video subtitles and quizzes, are …

Towards Knowledge-Based Personalized Product Description Generation in E-commerce

2019

Quality product descriptions are critical for providing competitive customer experience in an E-commerce platform. An accurate and attractive description not only helps customers make an informed decision but also improves the likelihood of purchase. However, …

A multi-label classification method using a hierarchical and transparent representation for paper-reviewer recommendation

2019 · arXiv (Cornell University)

Paper-reviewer recommendation task is of significant academic importance for conference chairs and journal editors. How to effectively and accurately recommend reviewers for the submitted papers is a meaningful and still tough task. In this paper, …

A Self-supervised Method for Entity Alignment

2021 · arXiv (Cornell University)

Entity alignment, aiming to identify equivalent entities across different knowledge graphs (KGs), is a fundamental problem for constructing large-scale KGs. Over the course of its development, supervision has been considered necessary for accurate alignments. Inspired …

P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks

2022

Prompt tuning, which only tunes continuous prompts with a frozen language model, substantially reduces per-task storage and memory usage at training. However, in the context of NLU, prior work reveals that prompt tuning does not …

Rethinking the Setting of Semi-supervised Learning on Graphs

2022 · arXiv (Cornell University)

We argue that the present setting of semisupervised learning on graphs may result in unfair comparisons, due to its potential risk of over-tuning hyper-parameters for models. In this paper, we highlight the significant influence of …

NetSMF: Large-Scale Network Embedding as Sparse Matrix Factorization

2019

We study the problem of large-scale network embedding, which aims to learn latent representations for network mining applications. Previous research shows that 1) popular network embedding benchmarks, such as DeepWalk, are in essence implicitly factorizing …

Representation Learning for Attributed Multiplex Heterogeneous Network

2019

Network embedding (or graph embedding) has been widely used in many real-world applications. However, existing methods mainly focus on networks with single-typed nodes/edges and cannot scale well to handle large networks. Many real-world networks consist …

Towards Knowledge-Based Recommender Dialog System

2019

Qibin Chen, Junyang Lin, Yichang Zhang, Ming Ding, Yukuo Cen, Hongxia Yang, Jie Tang. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language …

GCC

2020

Graph representation learning has emerged as a powerful technique for addressing real-world problems. Various downstream graph learning tasks have benefited from its recent developments, such as node classification, similarity search, and graph classification. However, prior …

Controllable Multi-Interest Framework for Recommendation

2020

Recently, neural networks have been widely used in e-commerce recommender systems, owing to the rapid development of deep learning. We formalize the recommender system as a sequential recommendation problem, intending to predict the next items …

P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks

2021 · arXiv (Cornell University)

Prompt tuning, which only tunes continuous prompts with a frozen language model, substantially reduces per-task storage and memory usage at training. However, in the context of NLU, prior work reveals that prompt tuning does not …

GLM: General Language Model Pretraining with Autoregressive Blank Infilling

2022 · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Zhengxiao Du, Yujie Qian, Xiao Liu, Ming Ding, Jiezhong Qiu, Zhilin Yang, Jie Tang. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

Parameter-efficient fine-tuning of large-scale pre-trained language models

2023 · Nature Machine Intelligence

Abstract With the prevalence of pre-trained language models (PLMs) and the pre-training–fine-tuning paradigm, it has been continuously shown that larger models tend to yield better performance. However, as PLMs scale up, fine-tuning and storing all …