Yue Zhang

Distance Metric Learning for Aspect Phrase Grouping

2016 · arXiv (Cornell University)

Aspect phrase grouping is an important task in aspect-level sentiment analysis. It is a challenging problem due to polysemy and context dependency. We propose an Attention-based Deep Distance Metric Learning (ADDML) method, by considering aspect …

A bilingual attention network for code-switched emotion prediction

2016 · PolyU Institutional Research Archive (Hong Kong Polytechnic University)

202208 bcch

Understanding Types of Cyberbullying in an Anonymous Messaging Application

2018

The possibility of anonymity and lack of effective ways to identify inappropriate messages have resulted in a significant amount of online interaction data that attempt to harass, bully, or offend the recipient. In this work, …

Improving Cross-Domain Chinese Word Segmentation with Word Embeddings

2019 · arXiv (Cornell University)

Cross-domain Chinese Word Segmentation (CWS) remains a challenge despite recent progress in neural-based CWS. The limited amount of annotated data in the target domain has been the key obstacle to a satisfactory performance. In this …

A Generic Human–Machine Annotation Framework Based on Dynamic Cooperative Learning

2019 · IEEE Transactions on Cybernetics

The task of obtaining meaningful annotations is a tedious work, incurring considerable costs and time consumption. Dynamic active learning and cooperative learning are recently proposed approaches to reduce human effort of annotating data with subjective …

Achieving Efficient and Secure Data Acquisition for Cloud-supported Internet of Things in Smart Grid

2018 · arXiv (Cornell University)

Cloud-supported Internet of Things (Cloud-IoT) has been broadly deployed in smart grid systems. The IoT front-ends are responsible for data acquisition and status supervision, while the substantial amount of data is stored and managed in …

In-Order Transition-based Constituent Parsing

2017 · Transactions of the Association for Computational Linguistics

Both bottom-up and top-down strategies have been used for neural transition-based constituent parsing. The parsing strategies differ in terms of the order in which they recognize productions in the derivation tree, where bottom-up strategies and …

Sentence-State LSTM for Text Representation

2018

Bi-directional LSTMs are a powerful tool for text representation. On the other hand, they have been shown to suffer various limitations due to their sequential nature. We investigate an alternative LSTM structure for encoding text, …

Design Challenges and Misconceptions in Neural Sequence Labeling

2018 · International Conference on Computational Linguistics

We investigate the design challenges of constructing effective and efficient neural sequence labeling systems, by reproducing twelve neural sequence labeling models, which include most of the state-of-the-art structures, and conduct a systematic model comparison on …

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.

Research on Government Information Sharing Model Using Blockchain Technology

2019

Research Purpose: The distributed, traceable and security of blockchain technology are applicable to the construction of new government information resource models, which could eliminate the barn effect and trust in government information sharing, as well …

Quantifying non-Gaussianity of bosonic fields via an uncertainty relation

2020 · Physical Review A

While Gaussian states and associated Gaussian operations are basic ingredients and convenient objects for continuous-variable quantum information, it is also realized that non-Gaussianity is an important resource for quantum information processing. The characterization and quantification …

SemEval-2020 Task 4: Commonsense Validation and Explanation

2020

In this paper, we present SemEval-2020 Task 4, Commonsense Validation and Explanation (ComVE), which includes three subtasks, aiming to evaluate whether a system can distinguish a natural language statement that makes sense to humans from …

Privacy Protection Strategy Based on Federated Learning for Smart Park Multi Energy Fusion System

2021

In order to realize the promotion of clean energy, the energy Internet which supports the efficient energy utilization has been widely concerned. While, the smart Park energy system to realize the highly coupling of energy, …

Research on Component Retrieval and Matching Methods

2022

Aiming at how to quickly retrieve the target component from the huge component library, this paper proposes a component retrieval method based on facet classification, which uses component keyword set to facet description of the …

Towards Fine-grained Causal Reasoning and QA

2022 · arXiv (Cornell University)

Understanding causality is key to the success of NLP applications, especially in high-stakes domains. Causality comes in various perspectives such as enable and prevent that, despite their importance, have been largely ignored in the literature. …

A Rationale-Centric Framework for Human-in-the-loop Machine Learning

2022 · arXiv (Cornell University)

We present a novel rationale-centric framework with human-in-the-loop -- Rationales-centric Double-robustness Learning (RDL) -- to boost model out-of-distribution performance in few-shot learning scenarios. By using static semi-factual generation and dynamic human-intervened correction, RDL exploits rationales …

Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

2023 · arXiv (Cornell University)

Harnessing logical reasoning ability is a comprehensive natural language understanding endeavor. With the release of Generative Pretrained Transformer 4 (GPT-4), highlighted as "advanced" at reasoning tasks, we are eager to learn the GPT-4 performance on …

Evaluating Open-QA Evaluation

2023 · arXiv (Cornell University)

This study focuses on the evaluation of the Open Question Answering (Open-QA) task, which can directly estimate the factuality of large language models (LLMs). Current automatic evaluation methods have shown limitations, indicating that human evaluation …

Plan, Verify and Switch: Integrated Reasoning with Diverse X-of-Thoughts

2023

As large language models (LLMs) have shown effectiveness with different prompting methods, such as Chain of Thought, Program of Thought, we find that these methods have formed a great complementarity to each other on math …

On Protecting the Data Privacy of Large Language Models (LLMs): A Survey

2024 · arXiv (Cornell University)

Large language models (LLMs) are complex artificial intelligence systems capable of understanding, generating and translating human language. They learn language patterns by analyzing large amounts of text data, allowing them to perform writing, conversation, summarizing …

RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation

2024 · arXiv (Cornell University)

Large Language Models (LLMs) demonstrate human-level capabilities in dialogue, reasoning, and knowledge retention. However, even the most advanced LLMs face challenges such as hallucinations and real-time updating of their knowledge. Current research addresses this bottleneck …

Data mining method for English classroom teaching quality based on hierarchical clustering

2024 · International Journal of Business Intelligence and Data Mining

English classroom teaching involves multiple types of data, and effectively collecting and organising these data is a challenging task. Therefore, a hierarchical clustering based data mining method for English classroom teaching quality is proposed. Firstly, …

ExploraCoder: Advancing code generation for multiple unseen APIs via planning and chained exploration

2024 · arXiv (Cornell University)

Large language models face intrinsic limitations in coding with APIs that are unseen in their training corpora. As libraries continuously evolve, it becomes impractical to exhaustively retrain LLMs with new API knowledge. This limitation hampers …

Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity

2025 · arXiv (Cornell University)

Graph anomaly detection (GAD) aims to identify nodes from a graph that are significantly different from normal patterns. Most previous studies are model-driven, focusing on enhancing the detection effect by improving the model structure. However, …

SWE-GPT: A Process-Centric Language Model for Automated Software Improvement

2025 · Proceedings of the ACM on software engineering.

Large language models (LLMs) have demonstrated remarkable performance in code generation, significantly enhancing the coding efficiency of developers. Recent advancements in LLM-based agents have led to significant progress in end-to-end automatic software engineering (ASE), particularly …

LOGicalThought: Logic-Based Ontological Grounding of LLMs for High-Assurance Reasoning

2025 · arXiv (Cornell University)

High-assurance reasoning, particularly in critical domains such as law and medicine, requires conclusions that are accurate, verifiable, and explicitly grounded in evidence. This reasoning relies on premises codified from rules, statutes, and contracts, inherently involving …

Time Tells All: Deanonymization of Blockchain RPC Users with Zero Transaction Fee (Extended Version)

2025 · arXiv (Cornell University)

Remote Procedure Call (RPC) services have become a primary gateway for users to access public blockchains. While they offer significant convenience, RPC services also introduce critical privacy challenges that remain insufficiently examined. Existing deanonymization attacks …

An Efficient Quantum Classifier Based on Hamiltonian Representations

2025 · TUbilio (Technical University of Darmstadt)

Quantum machine learning (QML) is a discipline that seeks to transfer the advantages of quantum computing to data-driven tasks. However, many studies rely on toy datasets or heavy feature reduction, raising concerns about their scalability. …

Starfish: Rebalancing Multi-Party Off-Chain Payment Channels

2025 · arXiv (Cornell University)

Blockchain technology has revolutionized the way transactions are executed, but scalability remains a major challenge. Payment Channel Network (PCN), as a Layer-2 scaling solution, has been proposed to address this issue. However, skewed payments can …

Gated Neural Networks for Targeted Sentiment Analysis

2016 · Proceedings of the AAAI Conference on Artificial Intelligence

Targeted sentiment analysis classifies the sentiment polarity towards each target entity mention in given text documents. Seminal methods extract manual discrete features from automatic syntactic parse trees in order to capture semantic information of the …

Automatic Features for Essay Scoring – An Empirical Study

2016

Essay scoring is a complicated processing requiring analyzing, summarizing and judging expertise. Traditional work on essay scoring focused on automatic handcrafted features, which are expensive yet sparse. Neural models offer a way to learn syntactic …

Attention-based Recurrent Convolutional Neural Network for Automatic Essay Scoring

2017

Neural network models have recently been applied to the task of automatic essay scoring, giving promising results. Existing work used recurrent neural networks and convolutional neural networks to model input essays, giving grades based on …

Word-Context Character Embeddings for Chinese Word Segmentation

2017

Neural parsers have benefited from automatically labeled data via dependencycontext word embeddings. We investigate training character embeddings on a word-based context in a similar way, showing that the simple method significantly improves state-of-the-art neural word …

End-to-End Neural Relation Extraction with Global Optimization

2017

Neural networks have shown promising results for relation extraction. State-ofthe-art models cast the task as an end-toend problem, solved incrementally using a local classifier. Yet previous work using statistical models have demonstrated that global optimization …

Leveraging Context Information for Natural Question Generation

2018

Linfeng Song, Zhiguo Wang, Wael Hamza, Yue Zhang, Daniel Gildea. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers). 2018.

N-ary Relation Extraction using Graph-State LSTM

2018

Cross-sentence n-ary relation extraction detects relations among n entities across multiple sentences. Typical methods formulate an input as a document graph, integrating various intra-sentential and inter-sentential dependencies. The current state-of-the-art method splits the input graph …

Semantic Neural Machine Translation Using AMR

2019 · Transactions of the Association for Computational Linguistics

Abstract It is intuitive that semantic representations can be useful for machine translation, mainly because they can help in enforcing meaning preservation and handling data sparsity (many sentences correspond to one meaning) of machine translation …

Cross-Domain NER using Cross-Domain Language Modeling

2019

Due to limitation of labeled resources, crossdomain named entity recognition (NER) has been a challenging task. Most existing work considers a supervised setting, making use of labeled data for both the source and target domains. …

College Library Personalized Recommendation System Based on Hybrid Recommendation Algorithm

2019 · Procedia CIRP

When the number of books provided by library is relatively large, it becomes difficult for user to select appropriate book from a lot of candidate books. In this case, this paper designs a personalized recommendation …

Chinese NER Using Lattice LSTM

2018

We investigate a lattice-structured LSTM model for Chinese NER, which encodes a sequence of input characters as well as all potential words that match a lexicon. Compared with character-based methods, our model explicitly leverages word …

A Graph-to-Sequence Model for AMR-to-Text Generation

2018

The problem of AMR-to-text generation is to recover a text representing the same meaning as an input AMR graph. The current state-of-the-art method uses a sequence-to-sequence model, leveraging LSTM for encoding a linearized AMR structure. …

Neural Word Segmentation with Rich Pretraining

2017

Neural word segmentation research has benefited from large-scale raw texts by leveraging them for pretraining character and word embeddings. On the other hand, statistical segmentation research has exploited richer sources of external information, such as …

LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning

2020

Machine reading is a fundamental task for testing the capability of natural language understand- ing, which is closely related to human cognition in many aspects. With the rising of deep learning techniques, algorithmic models rival …

DialogSum: A Real-Life Scenario Dialogue Summarization Dataset

2021

Proposal of large-scale datasets has facilitated research on deep neural models for news summarization. Deep learning can also be potentially useful for spoken dialogue summarization, which can benefit a range of reallife scenarios including customer …

Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter

2021

Wei Liu, Xiyan Fu, Yue Zhang, Wenming Xiao. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Template-Based Named Entity Recognition Using BART

2021

There is a recent interest in investigating fewshot NER, where the low-resource target domain has different label sets compared with a resource-rich source domain. Existing methods use a similarity-based metric. However, they cannot make full …

A Survey on Evaluation of Large Language Models

2024 · ACM Transactions on Intelligent Systems and Technology

Large language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications. As LLMs continue to play a vital role in both research and daily use, …