Sequence Labelling in Structured Domains with Hierarchical Recurrent Neural Networks
Proceedings of the Twentieth International Joint Conference on Artificial Intelligence. Pages 774-778.
Abstract
Modelling data in structured domains requires establishing the relations among patterns at multiple scales. When these patterns arise from sequential data, the multiscale structure also contains a dynamic component that must be modelled, particularly, as is often the case, if the data is unsegmented. Probabilistic graphical models are the predominant framework for labelling unsegmented sequential data in structured domains. Their use requires a certain degree of a priori knowledge about the relations among patterns and about the patterns themselves. This paper presents a hierarchical system, based on the connectionist temporal classification algorithm, for labelling unsegmented sequential data at multiple scales with recurrent neural networks only. Experiments on the recognition of sequences of spoken digits show that the system outperforms hidden Markov models, while making fewer assumptions about the domain.
@inproceedings{ijcai2007p124,
title = {Sequence Labelling in Structured Domains with Hierarchical Recurrent Neural Networks},
author = {Fernández, Santiago and Graves, Alex and Schmidhuber, Jürgen},
booktitle = {Proceedings of the Twentieth International Joint Conference on
Artificial Intelligence, {IJCAI-07}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Ramon López de Mántaras},
pages = {774--778},
year = {2007},
url = {https://ijcai.org/proceedings/2007/124},
}
TY - CPAPER TI - Sequence Labelling in Structured Domains with Hierarchical Recurrent Neural Networks AU - Fernández, Santiago AU - Graves, Alex AU - Schmidhuber, Jürgen T2 - Proceedings of the Twentieth International Joint Conference on Artificial Intelligence, IJCAI-07 PB - International Joint Conferences on Artificial Intelligence PY - 2007 SP - 774 EP - 778 UR - https://ijcai.org/proceedings/2007/124 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: