v34: ICGI 2014 Proceedings

2026-06-10 · Source: Proceedings of Machine Learning Research · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Computational Linguistics · Depth: Expert, quick

Summary

Volume 34 of the Proceedings of Machine Learning Research (PMLR) compiles the papers from "The 12th International Conference on Grammatical Inference," held from September 17-19, 2014, in Kyoto, Japan, edited by Alexander Clark, Makoto Kanazawa, and Ryo Yoshinaka. The conference featured invited talks on topics such as grammar compression and a rationalist theory of language acquisition. Accepted papers explored diverse areas including canonical semi-deterministic transducers, efficient algorithms for learning substitutable languages from positive examples, and improvements in spectral learning for probabilistic grammatical inference. Further contributions covered active automata learning, learning nondeterministic Mealy machines, maximizing tree series, and inferring probabilistic context-free grammars using minimum satisfiability and hierarchical Pitman-Yor processes, alongside an application of Directed Acyclic Word Graphs in bioinformatics.

Key takeaway

This volume from the 2014 International Conference on Grammatical Inference presents key advancements in algorithms for inferring formal grammars and automata. It details novel techniques like canonical semi-deterministic transducers, efficient learning of substitutable languages, and improved spectral methods, with applications spanning real-world data and bioinformatics. Researchers and practitioners in machine learning, NLP, and computational biology will find valuable insights into robust pattern recognition and language acquisition.

Topics

• Grammatical Inference
• Automata Learning
• Probabilistic Grammars
• Language Acquisition Theory
• Grammar Compression

Best for: AI Scientist, Research Scientist

Related on AIssential

• v153: Proceedings of ICGI 2020 — Volume 153 of the Proceedings of the Fifteenth International Conference on Grammatical Inference, held online from August 23-27, 2021, presents a collection of research papers edited by Jane Chandlee,…
• v217: Proceedings of ICGI 2023 — The 16th International Conference on Grammatical Inference (ICGI 2023), held from July 10-13, 2023, in Rabat, Morocco, presented a diverse program covering advancements in learning formal languages.
• A Zipf-preserving, long-range correlated surrogate for written language and other symbolic sequences — A new model generates symbolic sequence surrogates preserving both symbol frequencies and long-range correlations.
• Grammar as an Injectable: A Trojan Horse to NLP | Towards Data Science — CCG offers a non-statistical, algebraic framework for NLP, treating words as functions to ensure grammatical consistency and enhance interpretability.
• Neuro-Symbolic ODE Discovery with Latent Grammar Flow — LGF discovers ODEs from data by embedding grammar-based representations into a guided discrete latent space.
• N-Grams and Markov Assumptions: The First Predictive Models of Language — N-grams were the first predictive language models, using statistical counts over short word sequences to anticipate the next word.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Proceedings of Machine Learning Research.