Yi Yang

A Kind of Precision Recommendation Method for Massive Public Digital Cultural Resources: A Preliminary Report

2016

In this paper, we give a preliminary report regarding a precision recommendation method for massive public digital cultural resources, which help people find the resources they are really interested in. We classify the public digital …

Overcoming Language Variation in Sentiment Analysis with Social Attention

2015 · arXiv (Cornell University)

Variation in language is ubiquitous, particularly in newer forms of writing such as social media. Fortunately, variation is not random, it is often linked to social properties of the author. In this paper, we show …

Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentation

2019 · arXiv (Cornell University)

For unsupervised domain adaptation problems, the strategy of aligning the two domains in latent feature space through adversarial learning has achieved much progress in image classification, but usually fails in semantic segmentation tasks in which …

S-MART: Novel Tree-based Structured Learning Algorithms Applied to Tweet Entity Linking

2016 · arXiv (Cornell University)

Non-linear models recently receive a lot of attention as people are starting to discover the power of statistical and embedding features. However, tree-based models are seldom studied in the context of structured learning despite their …

Hidden Markov Random Field for Multi-Agent Optimal Decision in Top-Coal Caving

2020 · IEEE Access

Applying model-based learning for the optimal decision of the multi-agent system is not trivial due to the expensive price or even the impossibility of obtaining the ground truth for training the model of the complex …

Learning Numeracy: A Simple Yet Effective Number Embedding Approach Using Knowledge Graph

2021

Numeracy plays a key role in natural language understanding. However, existing NLP approaches, either traditional word2vec approach or contextualized transformer-based language models, fail to learn numeracy. As the result, the performance of these models is …

Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation

2022 · arXiv (Cornell University)

A thriving trend for domain adaptive segmentation endeavors to generate the high-quality pseudo labels for target domain and retrain the segmentor on them. Under this self-training paradigm, some competitive methods have sought to the latent-space …

Tele-Knowledge Pre-training for Fault Analysis

2022 · arXiv (Cornell University)

In this work, we share our experience on tele-knowledge pre-training for fault analysis, a crucial task in telecommunication applications that requires a wide range of knowledge normally found in both machine log data and product …

Combating Label Noise With A General Surrogate Model For Sample Selection

2023 · arXiv (Cornell University)

Modern deep learning systems are data-hungry. Learning with web data is one of the feasible solutions, but will introduce label noise inevitably, which can hinder the performance of deep neural networks. Sample selection is an …

CQIL: Inference Latency Optimization with Concurrent Computation of Quasi-Independent Layers

2024

The fast-growing large scale language models are delivering unprecedented performance on almost all natural language processing tasks.However, the effectiveness of large language models are reliant on an exponentially increasing number of parameters.The overwhelming computation complexity …

LLM-Empowered Few-Shot Node Classification on Incomplete Graphs with Real Node Degrees

2024

Graphs constructed from real-world scenarios are often incomplete due to privacy restrictions or resource limitations, posing significant challenges for node classification, especially when labeled data are scarce. In many scenarios of incomplete graphs, the real …

The Stringy Scaling Loop Expansion and Stringy Scaling Violation

2025 · Progress of Theoretical and Experimental Physics

Abstract We propose a systematic approximation scheme to calculate general string-tree level n-point hard string scattering amplitudes ($\text{HSSA}$) of open bosonic string theory. This stringy scaling loop expansion contains a finite number of vacuum diagram …

RSCF-PM: Relation-Specific Curvature Fields on Product Manifolds for Fraud Detection in Multi-Relational Social Networks

2026 · Mathematics

Graph-based fraud detection in multi-relational social networks must capture heterogeneous relation semantics and diverse fraud patterns while preserving geometric consistency and remaining scalable. Existing methods often either force all relations into a shared Euclidean or …

WikiQA: A Challenge Dataset for Open-Domain Question Answering

2015

We describe the WIKIQA dataset, a new publicly available set of question and sentence pairs, collected and annotated for research on open-domain question answering. Most previous work on answer sentence selection focuses on a dataset …

S-MART: Novel Tree-based Structured Learning Algorithms Applied to Tweet Entity Linking

2015

Yi Yang, Ming-Wei Chang. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2015.