Zuoyu Tian

Topic Modeling Natural Language Processing Techniques Speech Recognition and Synthesis Hate Speech and Cyberbullying Detection Online Learning and Analytics

Publications

Citations

389

Est. group size

—

Recurring co-author estimate

Active years

Publishing since 2019

Research summary

AI-generated

Zuoyu Tian works in natural language processing, the branch of computer science that helps computers understand and generate human language. Much of the research focuses on Chinese and multilingual language tasks, including building benchmarks and treebanks (annotated language datasets), studying speech patterns like Mandarin tones, and examining fairness in large language models. Recent work also connects these methods to practical applications such as improving access to scholarly information.

Natural language processingChinese and multilingual language understandingSpeech recognition and analysisLanguage benchmarks and datasetsFairness in language models

Publication activity was steady at around three to four papers per year from 2019 to 2022, dipped in 2023-2024, and returned to four in 2025.

Generated by claude-opus-4-8 from public bibliographic data · Jul 11, 2026

Publication cadence

Publications per year over the last 10 years — averaging 2.0/year recently

Recent publications

Code and data for "Fairness Evaluation of Large Language Models in Academic Library Reference Services"
arXiv (Cornell University) · 2025
Improving scholarship accessibility with reinforcement learning
Information Research an international electronic journal · 2025
Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings
2022
Mandarin Tone Sandhi Realization: Evidence from Large Speech Corpora
Interspeech 2022 · 2022
Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings
arXiv (Cornell University) · 2022
Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference
2021
BAHP: Benchmark of Assessing Word Embeddings in Historical Portuguese
2021
Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference
arXiv (Cornell University) · 2021
Building a Treebank for Chinese Literature for Translation Studies
2020
CLUE: A Chinese Language Understanding Evaluation Benchmark
2020
CLUE: A Chinese Language Understanding Evaluation Benchmark
arXiv (Cornell University) · 2020
Ensemble Methods to Distinguish Mainland and Taiwan
2019

Publishes in

arXiv (Cornell University)×6
Journal of Historical Linguistics×1
Information Research an international electronic journal×1
Language Resources and Evaluation×1
Interspeech 2022×1

This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.

Last updated Jul 11, 2026.

Claim or correct this profile