My research attempts to develop algorithmic, learning-based acounts of phonological rules and representations, usually from the perspective of language acquisition, using computational and experimental approaches. This involves identifying independently-established psychological mechanisms that could be at play in the process of linguistic development, and using these mechanisms as the components of computational learning algorithms. Such algorithms constitute hypotheses about the processes involved in human learning. Through evaluation of a hypothesized learning algorithm—in particular its accuracy generalizing to unseen test words, its predicted developmental patterns, and its predictions in experimental settings—the algorithm can be interpreted as providing a learning-based account of the rules and representations that it constructs along the way.
Publications
-
A Learning-Based Account of Phonological Tiers
Caleb Belth
Linguistic Inquiry, 2024.
[pdf]
[code]
[algophon]
-
A Learning-Based Account of Local Phonological Processes
Caleb Belth
Phonology, In Press.
[pdf]
-
Meaning-Informed Low-Resource Segmentation of Agglutinative Morphology
Caleb Belth
Society for Computation in Linguistics, 2024
[pdf] [code]
-
A Learning-Based Account of Non-Productivity in Dutch Voicing Alternations
Caleb Belth
Boston University Conference on Language Development, 2023
[pdf]
-
Towards a Learning-Based Account of Underlying Forms: A Case Study in Turkish
Caleb Belth
Society for Computation in Linguistics, 2023
[pdf]
[code]
-
The Greedy and Recursive Search for Morphological Productivity
Caleb Belth, Sarah Payne, Deniz Beser, Jordan Kodner, Charles Yang
CogSci, 2021
[pdf]
[code]
-
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.
[conference pdf]
[journal extension pdf]
[code]
-
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%)
[pdf]
[code]
[video]
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%)
[pdf]
[code]
[video]
-
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%)
[pdf]
-
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%)
[pdf]
[slides]
Also accepted for presentation at the 15th SIGKDD International Workshop on Mining and Learning with Graphs.