Search Results for author: Jeffrey Heinz

Found 17 papers, 3 papers with code

Finite-state Model of Shupamem Reduplication

no code implementations ACL (SIGMORPHON) 2021 Magdalena Markowska, Jeffrey Heinz, Owen Rambow

Shupamem, a language of Western Cameroon, is a tonal language which also exhibits the morpho-phonological process of full reduplication.

Why Linguistics Will Thrive in the 21st Century: A Reply to Piantadosi (2023)

no code implementations6 Aug 2023 Jordan Kodner, Sarah Payne, Jeffrey Heinz

We present a critical assessment of Piantadosi's (2023) claim that "Modern language models refute Chomsky's approach to language," focusing on four main points.

MLRegTest: A Benchmark for the Machine Learning of Regular Languages

1 code implementation16 Apr 2023 Sam van der Poel, Dakotah Lambert, Kalina Kostyszyn, Tiantian Gao, Rahul Verma, Derek Andersen, Joanne Chau, Emily Peterson, Cody St. Clair, Paul Fodor, Chihiro Shibata, Jeffrey Heinz

Evaluating machine learning (ML) systems on their ability to learn known classifiers allows fine-grained examination of the patterns they can learn, which builds confidence when they are applied to the learning of unknown classifiers.

The SIGMORPHON 2019 Shared Task: Morphological Analysis in Context and Cross-Lingual Transfer for Inflection

no code implementations WS 2019 Arya D. McCarthy, Ekaterina Vylomova, Shijie Wu, Chaitanya Malaviya, Lawrence Wolf-Sonkin, Garrett Nicolai, Christo Kirov, Miikka Silfverberg, Sabrina J. Mielke, Jeffrey Heinz, Ryan Cotterell, Mans Hulden

The SIGMORPHON 2019 shared task on cross-lingual transfer and contextual analysis in morphology examined transfer learning of inflection between 100 language pairs, as well as contextual lemmatization and morphosyntactic description in 66 languages.

Cross-Lingual Transfer Lemmatization +3

Learning with Partially Ordered Representations

no code implementations WS 2019 Jane Chandlee, Remi Eyraud, Jeffrey Heinz, Adam Jardine, Jonathan Rawski

This paper examines the characterization and learning of grammars defined with enriched representational models.

Modeling Reduplication with 2-way Finite-State Transducers

no code implementations WS 2018 Hossep Dolatian, Jeffrey Heinz

2-way FSTs can model reduplicative typology in a way which is convenient, easy to design and debug in practice, and linguistically-motivated.

Subregular Complexity and Deep Learning

1 code implementation16 May 2017 Enes Avcu, Chihiro Shibata, Jeffrey Heinz

Learning experiments were conducted with two types of Recurrent Neural Networks (RNNs) on six formal languages drawn from the Strictly Local (SL) and Strictly Piecewise (SP) classes.

Temporal Sequences

Learning Tier-based Strictly 2-Local Languages

no code implementations TACL 2016 Adam Jardine, Jeffrey Heinz

The Tier-based Strictly 2-Local (TSL2) languages are a class of formal languages which have been shown to model long-distance phonotactic generalizations in natural language (Heinz et al., 2011).

Learning Strictly Local Subsequential Functions

no code implementations TACL 2014 Ch, Jane lee, R{\'e}mi Eyraud, Jeffrey Heinz

We provide an automata-theoretic characterization of the ISL class and theorems establishing how the classes are related to each other and to Strictly Local languages.

Cannot find the paper you are looking for? You can Submit a new open access paper.