🧑‍🔬 Tao Shen

🏛️ Affiliations

🎓University of Technology SydneySydney · Australia2016–2025 · 57 papersEducation 2016–2021 · PhD in Computer ScienceEmployment 2020–2021 · Research AssistantEmployment 2023–2024 · Postdoc Research Fellowcurrent🏢MicrosoftRedmond · United States2022–2023 · 7 papers🎓Zhejiang UniversityHangzhou · China2020–2023 · 2 papers

🏛️Microsoft CorpBeijing · China2019–2022Employment 2019 · Research InternEmployment 2021–2022 · Applied Scientist

🏛️Microsoft CorpRedmond · United States2019Employment 2019 · Research Intern

🎓Chongqing University of Posts and TelecommunicationsChongqing · China2012–2016Education 2012–2016 · B.E in Communication Engineering

🏛️Didi Chuxing Technology CoBeijing · China2016Employment 2016 · Intern

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding (2017 · 854 citations)
   Sentence encoders in NLP usually rely on RNNs for long-range context or on CNNs for local patterns. Both have drawbacks: RNNs process tokens sequentially, and standard attention ignores word order. The authors propose DiSAN, a lightweight sentence-encoding network that uses only attention. It has two new components.…
2. Leveraging Large Language Models for NLG Evaluation: Advances and Challenges (2024 · 63 citations)
   Automatic metrics for natural language generation have serious limits. N-gram overlap scores such as BLEU and ROUGE mostly capture surface differences. Embedding-based metrics often agree poorly with human ratings and explain little about their scores. This EMNLP 2024 survey reviews the fast-growing use of LLMs as…
3. Large Language Models are Strong Zero-Shot Retriever (2023 · 26 citations)
   Zero-shot first-stage retrieval, where only a raw document collection is available and no labeled query–document pairs exist, usually trails supervised systems.
4. You Never Know a Person, You Only Know Their Defenses: Detecting Levels of Psychological Defense Mechanisms in Supportive Conversations (2026 · 15 citations)
   Psychological defenses are mostly automatic coping strategies. They shape what help seekers reveal and whether they accept or push back against support. Emotional support dialogue systems do not model them, and no public conversational dataset has been annotated with them. The authors address this gap with…
5. Multi-Session Client-Centered Treatment Outcome Evaluation in Psychotherapy (2026 · 4 citations)
   Most LLM-based evaluation of psychotherapy has focused on the therapist and looked at one session at a time.

All works

7 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. DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language UnderstandingProceedings of the AAAI Conference on Artificial IntelligenceTao Shen, Tianyi Zhou, Guodong Long, et al.2017 · 854 citations
2. Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base ↗Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · no summary yetTao Shen et al.2019 · 110 citations
3. Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning ↗Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · no summary yetTao Shen et al.2020 · 87 citations
4. Leveraging Large Language Models for NLG Evaluation: Advances and ChallengesConference on Empirical Methods in Natural Language Processing (EMNLP)Zhen Li, Xiaohan Xu, Tao Shen, et al.2024 · 63 citations
5. Large Language Models are Strong Zero-Shot RetrieverarXiv:2304.14233Tao Shen, Guodong Long, Xiubo Geng, et al.2023 · 26 citations
6. You Never Know a Person, You Only Know Their Defenses: Detecting Levels of Psychological Defense Mechanisms in Supportive ConversationsFindings of the Association for Computational LinguisticsHongbin Na, Zimu Wang, Zhaoming Chen, et al.2026 · 15 citations
7. Multi-Session Client-Centered Treatment Outcome Evaluation in PsychotherapyLanguage Resources and Evaluation Conference (LREC)Hongbin Na, Tao Shen, Shumao Yu, et al.2026 · 4 citations

🤝 Co-authors here

12 of 20 co-authors with a page, the most papers together first.

• Chongyang Tao ×2
• Guodong Long ×2
• Hongbin Na ×2
• Ling Chen ×2
• Tianyi Zhou ×2
• Can Xu
• Chengqi Zhang
• Daxin Jiang
• Jia-Chen Gu
• Jing Jiang
• John Torous
• Peilin Zhou

Venues

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

• Conference on Empirical Methods in Natural Language Processing (EMNLP) ×2: EMNLP 2024
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
• Language Resources and Evaluation Conference (LREC): LREC 2026
• Proceedings of the AAAI Conference on Artificial Intelligence: Proceedings of the AAAI Conference on Artificial Intelligence 2017
• Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

🔗 Cited by

Papers of our library cite their works 236 times (of the 149,439 papers whose bibliographies we read); 37 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

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