Xiaoyan Zhu
Xiaoyan Zhu has 3 papers in our library, in 2016–2022, most of them on Dialogue systems, Sentiment & emotion, Evaluation & benchmarks; often with Minlie Huang, Chujie Zheng, Hao Sun.
OpenAlex · ORCID · h-index 46 · 228 works · 10,618 citations OpenAlex, 2026-10-14
📄 3 works in our library · 🔗 Cited 461 times in our library · 3 more in our library without a page yet · ⭐ Paper Stars ranking: #970
Affiliations
Concepts, shelves and topics
📚 Shelves 8The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 3 worksArts and Humanities · 3 worksComputer Science · 3 worksLanguage and Linguistics · 3 worksDecision Sciences · 1 workManagement Science and Operations Research · 1 workSafety Research · 1 workSocial Sciences · 1 work
🧭 Topics 4Research subjects and languages the work is about.Sentiment & emotion · 1 workDialogue systems · 2 worksBias, fairness & safety · 1 workEvaluation & benchmarks · 1 work
💡 Concepts 1Key ideas and methods explained on our concept pages.Transformer and attention · 1 work
Works by year
2020s
2010s
Papers
- Attention-based LSTM for Aspect-level Sentiment Classification (2016 · 2,619 citations)
The paper addresses aspect-level sentiment classification, where a single sentence can carry different polarities toward different aspects, for example praise for food alongside criticism of service. - CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset (2020 · 146 citations)
Task-oriented dialogue research has relied mainly on English data. Even multi-domain corpora such as MultiWOZ link domains only through fixed constraints set in advance, and they lack user-side annotation. CrossWOZ addresses both gaps. It is the first large-scale Chinese cross-domain dialogue corpus, collected in a… - On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark (2022 · 102 citations)
Open-domain chatbots can produce replies that look harmless in isolation but become harmful given what the user said.
All works
- Attention-based LSTM for Aspect-level Sentiment ClassificationYequan Wang, Minlie Huang, Xiaoyan Zhu, et al.Conference on Empirical Methods in Natural Language Processing (EMNLP) · 2,619 citations
- CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue DatasetQi Zhu, Kaili Huang, Zheng Zhang, et al.Transactions of the Association for Computational Linguistics (TACL) · 146 citations
- JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs · original ↗ · no summary yet · Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021Pei Ke et al.2021 · 131 citations
- On the Safety of Conversational Models: Taxonomy, Dataset, and BenchmarkHao Sun, Guangxuan Xu, Jiawen Deng, et al.Findings of the Association for Computational Linguistics · 102 citations
- CPM-2: Large-scale Cost-effective Pre-trained Language Models · original ↗ · no summary yet · arXiv:2106.10715Zhengyan Zhang et al.2021 · 102 citations
- NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer · original ↗ · no summary yet · Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021Fei Huang et al.2021 · 26 citations
Co-authors here
Venues
- Findings of the Association for Computational Linguistics… ×2
- Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2016
- Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2022
- Transactions of the Association for Computational Linguistics (TACL): Transactions of the Association for Computational Linguistics (TACL) 2020
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/xiaoyan-zhu/