v57: ICGI 2016 Proceedings

2026-06-09 · Source: Proceedings of Machine Learning Research · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Expert, quick

Summary

This volume, PMLR 57, compiles the proceedings of The 13th International Conference on Grammatical Inference, held in Delft, The Netherlands, from October 5-7, 2016. The papers explore diverse aspects of grammatical inference, including the inference of various grammar types such as K-star Categorial Dependency Grammars and Context-Free Grammars, alongside automata learning methods like Query Learning Automata and the inference of Mealy Machines and Deterministic Finite Automata. Key research areas also encompass learning Top-Down Tree Transducers, addressing the Generalized Smallest Grammar Problem, and applying online grammar compression for frequent pattern discovery. Furthermore, the proceedings feature contributions on spectral learning for weighted automata, model theory applications in phonology, and several papers detailing results and methods from the "Sequence PredIction ChallengE (SPiCe)", utilizing techniques like LSTMs and neural network classifiers.

Key takeaway

The 13th International Conference on Grammatical Inference (ICGI 2016) presents diverse research on learning formal grammars and automata from data. Key contributions include novel methods for K-star Categorial Dependency Grammars, Query Learning Automata, spectral learning of weighted automata, and applications of LSTMs for sequence prediction. This collection offers valuable insights and tools for AI, NLP, and computational linguistics professionals developing robust models for language acquisition and pattern recognition.

Topics

• Grammatical Inference
• Automata Learning
• Sequence Prediction Challenge
• Context-Free Grammars
• Weighted Automata

Best for: AI Scientist, Research Scientist, NLP Engineer

Related on AIssential

• 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.
• 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,…
• 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.
• Datasets for Verb Alternations across Languages: BLM Templates and Data Augmentation Strategies — This work addresses the underexplored ability of large language models (LLMs) to capture cross-sentence paradigmatic patterns, specifically verb alternations.
• 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.
• Neuro-Symbolic ODE Discovery with Latent Grammar Flow — LGF discovers ODEs from data by embedding grammar-based representations into a guided discrete latent space.

Open in AIssential →

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