Grammar Interpretations and Learning TSL Online

Dakotah Lambert
Proceedings of the Fifteenth International Conference on Grammatical Inference, PMLR 153:81-91, 2021.

Abstract

The tier-based strictly local ($\TSL{}$) languages are a class of formal languages that, alongside the strictly piecewise class, effectively model some long-distance generalizations in natural language (Heinz et al., 2011). Two learning algorithms for $\TSL{}$ already exist: one by Jardine and Heinz (2016) and one by Jardine and McMullin (2017). The former is limited in that it cannot learn all $\TSL{}$ patterns. The latter is restricted to a batch-learning environment. We present a general algorithm without these limitations. In particular we show that $\TSL{}$ is efficiently learnable online via reinterpretation of a strictly local grammar, and this mechanism generalizes to the strictly piecewise class as well. However we note that the known $\TSL{}$ learning algorithms are not robust in the face of interaction with other constraints, posing a challenge for the utility of this class for phonotactics.

Cite this Paper

BibTeX
@InProceedings{pmlr-v153-lambert21a, title = {Grammar Interpretations and Learning TSL Online}, author = {Lambert, Dakotah}, booktitle = {Proceedings of the Fifteenth International Conference on Grammatical Inference}, pages = {81--91}, year = {2021}, editor = {Chandlee, Jane and Eyraud, Rémi and Heinz, Jeff and Jardine, Adam and van Zaanen, Menno}, volume = {153}, series = {Proceedings of Machine Learning Research}, month = {23--27 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v153/lambert21a/lambert21a.pdf}, url = {https://proceedings.mlr.press/v153/lambert21a.html}, abstract = {The tier-based strictly local ($\TSL{}$) languages are a class of formal languages that, alongside the strictly piecewise class, effectively model some long-distance generalizations in natural language (Heinz et al., 2011). Two learning algorithms for $\TSL{}$ already exist: one by Jardine and Heinz (2016) and one by Jardine and McMullin (2017). The former is limited in that it cannot learn all $\TSL{}$ patterns. The latter is restricted to a batch-learning environment. We present a general algorithm without these limitations. In particular we show that $\TSL{}$ is efficiently learnable online via reinterpretation of a strictly local grammar, and this mechanism generalizes to the strictly piecewise class as well. However we note that the known $\TSL{}$ learning algorithms are not robust in the face of interaction with other constraints, posing a challenge for the utility of this class for phonotactics.} }
Endnote
%0 Conference Paper %T Grammar Interpretations and Learning TSL Online %A Dakotah Lambert %B Proceedings of the Fifteenth International Conference on Grammatical Inference %C Proceedings of Machine Learning Research %D 2021 %E Jane Chandlee %E Rémi Eyraud %E Jeff Heinz %E Adam Jardine %E Menno van Zaanen %F pmlr-v153-lambert21a %I PMLR %P 81--91 %U https://proceedings.mlr.press/v153/lambert21a.html %V 153 %X The tier-based strictly local ($\TSL{}$) languages are a class of formal languages that, alongside the strictly piecewise class, effectively model some long-distance generalizations in natural language (Heinz et al., 2011). Two learning algorithms for $\TSL{}$ already exist: one by Jardine and Heinz (2016) and one by Jardine and McMullin (2017). The former is limited in that it cannot learn all $\TSL{}$ patterns. The latter is restricted to a batch-learning environment. We present a general algorithm without these limitations. In particular we show that $\TSL{}$ is efficiently learnable online via reinterpretation of a strictly local grammar, and this mechanism generalizes to the strictly piecewise class as well. However we note that the known $\TSL{}$ learning algorithms are not robust in the face of interaction with other constraints, posing a challenge for the utility of this class for phonotactics.
APA
Lambert, D.. (2021). Grammar Interpretations and Learning TSL Online. Proceedings of the Fifteenth International Conference on Grammatical Inference, in Proceedings of Machine Learning Research 153:81-91 Available from https://proceedings.mlr.press/v153/lambert21a.html.

Related Material