🧑‍🔬 Gokhan Tur

🏛️ Affiliations

🎓University of Illinois Urbana-ChampaignUrbana · United States2024–2026 · 19 paperscurrent🔬SRI InternationalMenlo Park · United States1999–2011 · 38 papers🏢MicrosoftRedmond · United States2010–2017 · 36 papers🏢AT&TBedminster · United States2002–2018 · 23 papers🏢AmazonSeattle · United States2020–2025 · 14 papers🎓Institute of Electrical and Electronics EngineersPiscataway · United States2010–2014 · 14 papers🎓Bilkent UniversityAnkara · Türkiye1997–2001 · 11 papers🏢Uber AISan Francisco · United States2018–2020 · 8 papers🏢GoogleMountain View · United States2016–2018 · 8 papers🎓RWTH Aachen UniversityAachen · Germany2020 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 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. Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems (2018 · 212 citations)
   Task-oriented dialogue agents are often pre-trained with supervised learning on dialogue corpora and then refined with reinforcement learning (RL) from user feedback.
2. Bootstrapping a Neural Conversational Agent with Dialogue Self-Play, Crowdsourcing and On-Line Reinforcement Learning (2018 · 181 citations)
   The paper addresses a practical obstacle for task-oriented conversational agents. End-to-end neural models need large annotated dialogue corpora, which are costly to build for every new domain. Wizard-of-Oz collection also often misses dialogue flows a developer expects the agent to handle.
3. Can You be More Social? Injecting Politeness and Positivity into Task-Oriented Conversational Agents (2020 · 10 citations)
   Task-oriented dialogue systems are usually built to deliver correct content and mostly ignore the social side of language.
4. GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems (2026)
   LLM-based multi-agent systems often fail to beat strong single-agent setups. One key reason is that when the final answer is wrong, it is hard to tell which agent or which interaction step caused the error. Existing optimizers mostly use only overall task success as feedback. The authors propose Gradient-Based…

All works

10 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

1. Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue SystemsConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Bing Liu, Gokhan Tür, Dilek Hakkani-Tür, et al.2018 · 212 citations
2. Bootstrapping a Neural Conversational Agent with Dialogue Self-Play, Crowdsourcing and On-Line Reinforcement LearningConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Pararth Shah, Dilek Hakkani-Tür, Bing Liu, et al.2018 · 181 citations
3. AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq ModelarXiv:2208.01448 · original ↗ · no summary yetSaleh Soltan et al.2022 · 83 citations
4. Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language ModelProceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · original ↗ · no summary yetEmre Can Acikgoz et al.2025 · 13 citations
5. Can You be More Social? Injecting Politeness and Positivity into Task-Oriented Conversational AgentsarXiv:2012.14653Yi-Chia Wang, Alexandros Papangelis, Runze Wang, et al.2020 · 10 citations
6. Tagging English by Path Voting Constraints36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, Volume 2 · original ↗ · no summary yetGökhan Tür, Kemal Oflazer1998 · 9 citations
7. Goal Alignment in LLM-Based User Simulators for Conversational AITransactions of the Association for Computational Linguistics · original ↗ · no summary yetShuhaib Mehri et al.2026 · 3 citations
8. Current Agents Fail to Leverage World Model as Tool for ForesightProceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · original ↗ · no summary yetCheng Qian et al.2026 · 1 citation
9. Prior Beliefs Prejudice LLM-as-Judge: Evidence from Persuasion EvaluationFindings of the Association for Computational Linguistics: ACL 2026 · original ↗ · no summary yetPardis Sadat Zahraei et al.2026 · 1 citation
10. GBC: Gradient-Based Connections for Optimizing Multi-Agent SystemsAnnual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)Xiaocheng Yang, Abdulrahman Alrabah, Dilek Hakkani-Tür, et al.2026

🤝 Co-authors here

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

• Dilek Hakkani-Tür ×3
• Bing Liu ×2
• Pararth Shah ×2
• Alexandros Papangelis
• Yi-Chia Wang

Venues

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

• Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) ×2: NAACL 2018 ×2
• Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) ×2
• 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, Volume 2
• Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL): SIGDIAL 2026
• Findings of the Association for Computational Linguistics: ACL 2026
• Transactions of the Association for Computational Linguistics

🔗 Cited by

Papers of our library cite their works 202 times (of the 141,840 papers whose bibliographies we read); 22 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/gokhan-tur/