Dr Jonathan Kummerfeld
School of Computer Science
Jonathan K. Kummerfeld is a Senior Lecturer (ie., research tenure-track Assistant Professor) in the School of Computer Science at the University of Sydney. He works on Natural Language Processing, with a particular focus on systems for collaboration between people and AI models, including in dialogue and crowdsourcing.
Jonathan K. Kummerfeld works on making computers capable of understanding language and using that ability to collaborate with people more effectively. This involves solving challenges in Artificial Intelligence and Human-Computer Interaction.
"My research projects fall into three core areas:
Interactive Executable Semantic Parsing - Developing systems that can take complex actions in response to user requests. For example, a person asks for information and the system queries a database to provide an answer, which involves accurately interpreting the request and determining the best way to present the answer.
Data Science - Making it possible to use NLP technology to analyse new forms of data, broadening the range of questions we can answer. Real-world data is messier than the benchmarks used in most NLP research, posing new challenges for our methods.
Communication and Collaboration - Exploring how AI systems can be active collaborators with people. For example, by building bots to play the board game Diplomacy, in which players chat to negotiate alliances, strategies, and tactics.
Solving these challenges involves innovation in (1) AI models, including neural networks, (2) data creation methods, such as crowdsourcing, and (3) research methodology, e.g., metrics for performance."
COMP5046: Natural Language Processing
Project title | Research student |
---|---|
Answerability, Calibration and Grounding Guarantees for Natural Language Question Answering | Kent O'SULLIVAN |
Publications
Book Chapters
- Gunasekara, C., Kummerfeld, J., Polymenakos, L., Lasecki, W. (2019). DSTC7 Task 1: Noetic End-to-End Response Selection. Dialog System Technology Challenges at AAAI 2019, (pp. 60-67). Florence, Italy: Association for Computational Linguistics (ACL). [More Information]
Journals
- Kim, S., Galley, M., Gunasekara, C., Lee, S., Atkinson, A., Peng, B., Schulz, H., Gao, J., Li, J., Adada, M., et al (2021). Overview of the Eighth Dialog System Technology Challenge: DSTC8. IEEE/ACM Transactions on Audio Speech and Language Processing, 29, 2529-2540. [More Information]
- Burdick, L., Kummerfeld, J., Mihalcea, R. (2021). To Batch or Not to Batch? Comparing Batching and Curriculum Learning Strategies across Tasks and Datasets. Journal of Mathematics, 9(18).
- Burdick, L., Kummerfeld, J., Mihalcea, R. (2021). To batch or not to batch? Comparing batching and curriculum learning strategies across tasks and datasets. Mathematics, 9(18). [More Information]
Conferences
- Jiang, Y., Zhu, H., Kummerfeld, J., Li, Y., Lasecki, W. (2022). A Novel Workflow for Accurately and Efficiently Crowdsourcing Predicate Senses and Argument Labels. Findings of the Association for Computational Linguistics, United States: Association for Computational Linguistics (ACL).
- Kummerfeld, J. (2022). Leveraging Similar Users for Personalized Language Modeling with Limited Data. 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers, United States of America: Association for Computational Linguistics (ACL).
- Kummerfeld, J., Bansal, M., Burkett, D., Klein, D. (2022). Mention Detection: Heuristics for the OntoNotes annotations. 15th Conference on Computational Natural Language Learning, Stroudsburg, Pennsylvania, United States: Association for Computational Linguistics (ACL).
2022
- Jiang, Y., Zhu, H., Kummerfeld, J., Li, Y., Lasecki, W. (2022). A Novel Workflow for Accurately and Efficiently Crowdsourcing Predicate Senses and Argument Labels. Findings of the Association for Computational Linguistics, United States: Association for Computational Linguistics (ACL).
- Kummerfeld, J. (2022). Leveraging Similar Users for Personalized Language Modeling with Limited Data. 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers, United States of America: Association for Computational Linguistics (ACL).
- Kummerfeld, J., Bansal, M., Burkett, D., Klein, D. (2022). Mention Detection: Heuristics for the OntoNotes annotations. 15th Conference on Computational Natural Language Learning, Stroudsburg, Pennsylvania, United States: Association for Computational Linguistics (ACL).
2021
- Burdick, L., Kummerfeld, J., Mihalcea, R. (2021). Analyzing the Surprising Variability in Word Embedding Stability Across Languages. 2021 Conference on Empirical Methods in Natural Language Processing, Dominican Republic: Empirical Methods in Natural Language Processing.
- Lahnala, A., Kambhatla, G., Peng, J., Whitehead, M., Minnehan, G., Guldan, E., Kummerfeld, J., Camcı, A., Mihalcea, R. (2021). Chord Embeddings: Analyzing What They Capture and Their Role for Next Chord Prediction and Artist Attribute Prediction. 10th International Conference on Artificial Intelligence in Music, Sound, Art and Design, Online: Springer. [More Information]
- Huffaker, J., Kummerfeld, J., Lasecki, W., Ackerman, M. (2021). Crowdsourced Detection of Emotionally Manipulative Language. 2020 ACM CHI Conference on Human Factors in Computing Systems (CHI EA 2020), Honolulu: Association for Computing Machinery (ACM). [More Information]
2020
- Welch, C., Kummerfeld, J., Perez-Rosas, V., Mihalcea, R. (2020). Compositional Demographic Word Embeddings. 2020 Conference on Empirical Methods in Natural Language Processing, United States: Association for Computational Linguistics (ACL).
- Welch, C., Kummerfeld, J., Perez-Rosas, V., Mihalcea, R. (2020). Exploring the Value of Personalized Word Embeddings. Proceedings of the 28th International Conference on Computational Linguistics, United States: International Committee on Computational Linguistics. [More Information]
- Welch, C., Mihalcea, R., Kummerfeld, J. (2020). Improving Low Compute Language Modeling with In-Domain Embedding Initialisation. 2020 Conference on Empirical Methods in Natural Language Processing, United States: Association for Computational Linguistics (ACL).
2019
- Kummerfeld, J., Gouravajhala, S., Peper, J., Athreya, V., Gunasekara, C., Ganhotra, J., Patel, S., Polymenakos, L., Lasecki, W. (2019). A Large-Scale Corpus for Conversation Disentanglement. 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019), Stroudsburg: Association for Computational Linguistics (ACL). [More Information]
- Larson, S., Mahendran, A., Peper, J., Clarke, C., Lee, A., Hill, P., Kummerfeld, J., Leach, K., Laurenzano, M., Tang, L., et al (2019). An Evaluation for Intent Classification and Out-of-Scope Prediction. 2019 Conference on Empirical Methods in Natural Language Processing, Hong Kong: Association for Computational Linguistics (ACL). [More Information]
- Gunasekara, C., Kummerfeld, J., Polymenakos, L., Lasecki, W. (2019). DSTC7 Task 1: Noetic End-to-End Response Selection. Dialog System Technology Challenges at AAAI 2019, (pp. 60-67). Florence, Italy: Association for Computational Linguistics (ACL). [More Information]
2018
- Kang, Y., Zhang, Y., Kummerfeld, J., Tang, L., Mars, J. (2018). Data Collection for a Production Dialogue System: A Startup Perspective. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3, New Orleans - Louisiana: Association for Computational Linguistics (ACL). [More Information]
- Jiang, Y., Finegan-Dollak, C., Kummerfeld, J., Lasecki, W. (2018). Effective crowdsourcing for a new type of summarization task. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3, New Orleans - Louisiana: Association for Computational Linguistics (ACL).
- Wendlandt, L., Kummerfeld, J., Mihalcea, R. (2018). Factors Influencing the Surprising Instability of Word Embeddings. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3, New Orleans - Louisiana: Association for Computational Linguistics (ACL).
2017
- Durrett, G., Kummerfeld, J., Berg-Kirkpatrick, T., Portnoff, R., Afroz, S., McCoy, D., Levchenko, K., Paxson, V. (2017). Identifying Products in Online Cybercrime Marketplaces: A Dataset for Fine-grained Domain Adaptation. Conference on Empirical Methods in Natural Language Processing, United States: Association for Computational Linguistics (ACL). [More Information]
- Kummerfeld, J., Klein, D. (2017). Parsing with Traces: An O(n4) Algorithm and a Structural Representation. ACL Anthology, 5, 441-454. [More Information]
- Portnoff, R., Kummerfeld, J., Afroz, S., Berg-Kirkpatrick, T., Durrett, G., McCoy, D., Levchenko, K., Paxson, V. (2017). Tools for Automated Analysis of Cybercriminal Markets. 26th International World Wide Web Conference (WWW 2017), Perth, WA: Association for Computing Machinery (ACM). [More Information]
2015
- Kummerfeld, J., Berg-Kirkpatrick, T., Klein, D. (2015). An Empirical Analysis of Optimization for Max-Margin NLP. 2015 Conference on Empirical Methods in Natural Language Processing, United States of America: Association for Computational Linguistics (ACL).
2013
- Kummerfeld, J., Tse, D., Curran, J., Klein, D. (2013). An Empirical Examination of Challenges in Chinese Parsing. 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013), Stroudsburg, PA USA: Association for Computational Linguistics (ACL).
- Moss, V., McClure-Griffiths, N., Murphy, T., Pisano, D., Kummerfeld, J., Curran, J. (2013). High-Velocity Clouds in the Galactic All Sky Survey. I. Catalog. The Astrophysical Journal Supplement Series, 209(1), 1-18. [More Information]
2012
- Kummerfeld, J., Hall, D., Curran, J., Klein, D. (2012). Parser Showdown at the Wall Street Corral: An Empirical Investigation of Error Types in Parser Output. Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (emnlp-conll 2012), Stroudsburg, PA: Association for Computational Linguistics (ACL).
- Kummerfeld, J., Klein, D., Curran, J. (2012). Robust Conversion of CCG Derivations to Phrase Structure Trees. The 50th Annual Meeting of the Association for Computational Linguistics (ACL 2012), Stroudsburg: Association for Computational Linguistics (ACL).
2010
- Kummerfeld, J., Roesner, J., Dawborn, T., Haggerty, J., Curran, J., Clark, S. (2010). Faster Parsing by Supertagger Adaptation. 48th Annual Meeting of the Association for Computational Linguistics (ACL 2010), Sweden: Association for Computational Linguistics (ACL).
- Honnibal, M., Kummerfeld, J., Curran, J. (2010). Morphological analysis can improve a CCG parser for English. 23rd International Conference on Computational Linguistics, Beijing, China: Press of Tsinghua University.
- Candelier, R., Widmer-Cooper, A., Kummerfeld, J., Dauchot, O., Biroli, G., Harrowell, P., Reichman, D. (2010). Spatiotemporal hierarchy of relaxation events, dynamical heterogeneities, and structural reorganization in a supercooled liquid. Physical Review Letters, 105(13), 135702-1-135702-4. [More Information]
2009
- Kummerfeld, J., Curran, J., Roesner, J. (2009). Faster parsing and supertagging model extimation. Australasian Language Technology Association Workshop (ALTA 2009), Australia: Australasian Language Technology Association.
2008
- Kummerfeld, J., Curran, J. (2008). Classification of Verb-Particle Constructions with the Google Web1T Corpus. Australasian Language Technology Association Workshop 2008 (ALTA), Australia: Australasian Language Technology Association.
- Kummerfeld, J., Hudson, T., Harrowell, P. (2008). The Densest Packing of AB Binary Hard-Sphere Homogeneous Compounds across all Size Ratios. The Journal of Physical Chemistry B, 112(35), 10773-10776. [More Information]
Selected Grants
2024
- Complementing Human Intelligence to Recognize Opponent Narratives (CHIRON), Kummerfeld J, Defense Advanced Research Projects Agency (USA)/Research Support
2023
- Making Sense of Language Model Outputs for End User Tasks, Kummerfeld J, Amazon Science/Amazon Research Awards Program
- Efficient Annotation through New Task Decomposition and Recombination Methods, Kummerfeld J, Google Asia Pacific Pte. Ltd/Research Support