🧑‍🔬 Kai Yu

🏛️ Affiliations

🎓Shanghai Jiao Tong UniversityShanghai · China2012–2026 · 228 papersEmployment · Professor, Computer Sciencecurrent🎓Yanshan UniversityQinhuangdao · China2024–2026 · 2 paperscurrent🎓University of CambridgeCambridge · United Kingdom2004–2012 · 44 papers🎓Heilongjiang UniversityHarbin · China2019–2021 · 7 papers🎓National University of Defense TechnologyChangsha · China2011–2019 · 4 papers🎓Northwest UniversityXi'an · China2015 · 3 papers🏛️Chinese Academy of SciencesBeijing · China2021–2024 · 2 papers🎓University of Chinese Academy of SciencesBeijing · China2021–2024 · 2 papers🏛️Agency for Science, Technology and ResearchSingapore · Singapore2023 · 2 papers🔬Allen Institute for Artificial IntelligenceSeattle · United States2023 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 25 more institutions on single bylines are not listed.

🧭 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📅 Works by year

2020s

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. Bidirectional LSTM-CRF Models for Sequence Tagging (2015 · 3,818 citations)
   This 2015 Baidu Research paper looks at sequence tagging (part-of-speech tagging, chunking and named entity recognition) with recurrent neural networks instead of linear models such as HMM, MEMM and CRF.
2. LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations (2021 · 191 citations)
   Text-to-SQL systems must jointly encode a natural-language question and a database schema of tables and columns, which form a heterogeneous graph.
3. Towards Universal Dialogue State Tracking (2018 · 191 citations)
   The paper tackles dialogue state tracking (DST), which means estimating a user's goal as slot-value pairs at each turn of a task-oriented spoken dialogue.
4. F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (2025 · 152 citations)
   F5-TTS is a fully non-autoregressive zero-shot text-to-speech system. It drops the usual alignment machinery: no duration model, no text encoder, and no phoneme alignment. Like E2 TTS, it turns the transcript into a character sequence, pads it with filler tokens to the length of the mel spectrogram, and trains a…
5. Is LLM a Reliable Reviewer? A Comprehensive Evaluation of LLM on Automatic Paper Reviewing Tasks (2024 · 73 citations)
   The paper asks whether large language models can be trusted as automatic peer reviewers, a question earlier review datasets did not answer well because they did not verify that generated reviews were correct.

All works

11 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them.

1. Bidirectional LSTM-CRF Models for Sequence TaggingarXiv:1508.01991Zhiheng Huang, Wei Xu, Kai Yu2015 · 3,818 citations
2. LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local RelationsAnnual Meeting of the Association for Computational Linguistics (ACL)Ruisheng Cao, Lu Chen, Zhi Chen, et al.2021 · 191 citations
3. Towards Universal Dialogue State TrackingConference on Empirical Methods in Natural Language Processing (EMNLP)Liliang Ren, Kaige Xie, Lu Chen, et al.2018 · 191 citations
4. F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow MatchingAnnual Meeting of the Association for Computational Linguistics (ACL)Yushen Chen, Zhikang Niu, Ziyang Ma, et al.2025 · 152 citations
5. SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific ResearcharXiv:2308.13149 · original ↗ · no summary yetLiangtai Sun et al.2023 · 89 citations
6. Is LLM a Reliable Reviewer? A Comprehensive Evaluation of LLM on Automatic Paper Reviewing TasksLanguage Resources and Evaluation Conference (LREC)Ruiyang Zhou, Lu Chen, Kai Yu2024 · 73 citations
7. Unsupervised Dual Paraphrasing for Two-stage Semantic ParsingProceedings of the 58th Annual Meeting of the Association for Computational Linguistics · original ↗ · no summary yetRuisheng Cao et al.2020 · 66 citations
8. Semi-Supervised Text Simplification with Back-Translation and Asymmetric Denoising AutoencodersarXiv:2004.14693 · original ↗ · no summary yetYanbin Zhao et al.2020 · 57 citations
9. Line Graph Enhanced AMR-to-Text Generation with Mix-Order Graph Attention NetworksProceedings of the 58th Annual Meeting of the Association for Computational Linguistics · original ↗ · no summary yetYanbin Zhao et al.2020 · 45 citations
10. Alignment for Efficient Tool Calling of Large Language ModelsProceedings of the 2025 Conference on Empirical Methods in Natural Language Processing · original ↗ · no summary yetHongshen Xu et al.2025 · 13 citations
11. TeCS: A Dataset and Benchmark for Tense Consistency of Machine TranslationProceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · original ↗ · no summary yetYiming Ai et al.2023 · 1 citation

🤝 Co-authors here

8 co-authors with a page, the most papers together first.

• Lu Chen ×3
• Jian Zhao
• Kaige Xie
• Ruisheng Cao
• Wei Xu
• Yanbin Zhao
• Zhi Chen
• Zhiheng Huang

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×5: ACL 2025, ACL 2021
• Conference on Empirical Methods in Natural Language Processing (EMNLP) ×2: EMNLP 2018
• Language Resources and Evaluation Conference (LREC): LREC 2024

🔗 Cited by

Papers of our library cite their works 1,079 times (of the 141,840 papers whose bibliographies we read); 82 citing papers with a page here →.

Updated 24 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/kai-yu/