Welcome! I'm a PhD candidate at the University of Michigan.
My thesis work is developing an algorithmic approach to phonology, in which phonological generalizations and representations are the result of learning algorithms grounded in independent psychological mechanisms. Informed by linguistic theory, psycholinguistics, and language acquisition, I use computational models as explicit, testable hypotheses. I evaluate my models on natural-language data, such as child-directed speech. In doing so, I compare the model’s behavior to linguistic analyses of the phenomenon and language acquisition results. Moreover, by taking an explicit, computational approach, my models make predictions, which I evaluate by comparing to human behavior in psycholinguistic experiments.
For my research, I have been awarded an NSF GRF, an NDSEG fellowship, and a Richard F. and Eleanor A. Towner Prize for Distinguished Academic Achievement.
Prior research has contributed methods for choosing unlinked pairs of nodes to investigate further with a link prediction
method or experimental study, identifying subtle patterns in networks that are too infrequent to be discovered by frequency alone,
and for discovering errors and missing information in incomplete knowledge graphs.
Applications of this work include anomaly detection, suspicious behavior discovery, and city/urban planning, including projects with the City of Detroit on transportation planning.
Feel free to contact me at firstname.lastname@example.org.
The Greedy and Recursive Search for Morphological Productivity
Caleb Belth, Sarah Payne, Deniz Beser, Jordan Kodner, Charles Yang
A Hidden Challenge of Link Prediction: Which Pairs to Check?
Caleb Belth, Alican Büyükçakır, Danai Koutra
IEEE International Conference on Data Mining (ICDM), 2020 (acceptance rate: 9.8%)
Selected as one of the best papers at ICDM 2020. Invited for publication at the KAIS Journal, Springer.
[journal extension pdf]
Mining Persistent Activity in Continually Evolving Networks.
Caleb Belth, Xinyi (Carol) Zheng, Danai Koutra
ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), August 2020 (acceptance rate 17%)
Also accepted for presentation at the 16th SIGKDD International Workshop on Mining and Learning with Graphs.
What is Normal, What is Strange, and What is Missing in a Knowledge Graph: Unified Characterization via Inductive Summarization.
Caleb Belth, Xinyi (Carol) Zheng, Jilles Vreeken, Danai Koutra
ACM The Web Conference (WWW), April 2020 (oral presentation, acceptance rate 19%)
Personalized Knowledge Graph Summarization: From the Cloud to Your Pocket
Tara Safavi, Caleb Belth, Lukas Faber, Davide Mottin, Emmanuel Muller, Danai Koutra
IEEE International Conference on Data Mining (ICDM), 2019 (acceptance rate: 9%)
When to Remember Where You Came from: Node Representation Learning in Higher-order Networks
Caleb Belth, Fahad Kamran, Donna Tjandra, Danai Koutra
IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), 2019 (acceptance rate: 15%)
Also accepted for presentation at the 15th SIGKDD International Workshop on Mining and Learning with Graphs.
How a proclivity for adjacency can drive the learning of non-local alternations.
Learning Non-Local Phonological Alternations via Automatic Creation of Tiers.
Cognitive Modeling and Computational Linguistics workshop at ACL, 2022.
Searching for Morphological Productivity.
Sarah Payne, Caleb Belth, Jordan Kodner, & Charles Yang.
The 96th Meeting of the Linguistics Society of America, 2022.
A rock comedian. [image]
Categories: Philosophy, Consciousness