Learning from the computational modelling of Plains Cree verbs

@article{Harrigan2017LearningFT,
  title={Learning from the computational modelling of Plains Cree verbs},
  author={Atticus Harrigan and Katherine Schmirler and Antti Arppe and Lene Antonsen and Trond Trosterud and Arok Wolvengrey},
  journal={Morphology},
  year={2017},
  volume={27},
  pages={565-598}
}
This paper describes the ongoing process of creating a computational morphological model of Plains Cree, a language native to North America, making use of finite-state machines, and with a focus on verbs. We cover prior linguistic theoretical and descriptive models of Plains Cree, moving on to the computational implementation of (chiefly) inflectional phenomena, followed by relevant morphophonological processes. We evaluate the performance of our computational implementation with a hand… 
On the Computational Modelling of Michif Verbal Morphology
TLDR
A language model such as LI VERB KAA-OOSHITAHK DI MICHIF furthers the goals of Indigenous computational linguistics in Canada while also supporting the creation of tools for documentation, education, and revitalization that are desired by the Métis community.
Modeling Northern Haida Verb Morphology
TLDR
The development of a computational model of the morphology of Northern Haida based on finite state machines (FSMs), with a focus on verbs, is described, while contextualizing the endeavour in the description, documentation and revitalization of First Nations Languages in Canada.
Interactive Word Completion for Plains Cree
TLDR
An approach to morph-based auto-completion based on a finite state morphological analyzer of Plains Cree shows the portability of the concept to a much larger, more complete morphological transducer, and proposes and compares various novel ranking strategies on the morph auto-complete output.
Building a Constraint Grammar Parser for Plains Cree Verbs and Arguments
TLDR
Syntactic modelling of verb and argument relationships in Plains Cree is demonstrated to be a straightforward process, though various semantic and pragmatic features should improve the current parser considerably.
Interactive Word Completion for Morphologically Complex Languages
TLDR
A method for morphologically-aware text input in Kunwinjku, a polysynthetic language of northern Australia, is developed and an existing finite state recognizer is modified to map input morph prefixes to morph completions, respecting the morphosyntax and morphophonology of the language.
BabyFST - Towards a Finite-State Based Computational Model of Ancient Babylonian
TLDR
A general finite-state based morphological model for Babylonian, a southern dialect of the Akkadian language, that can achieve a coverage up to 97.3% and recall up to 93.7% on lemmatization and POS-tagging task on token level from a transcribed input is described.
CKMorph: A Comprehensive Morphological Analyzer for Central Kurdish
TLDR
A comprehensive morphological analyzer for Central Kurdish (CK), a low­resourced language with a rich morphology, based on finite­state transducers is introduced and collected, manually labeled, and publicly shared test sets for evaluating accuracy and coverage of the analyzer.
Natural Language Generation for Polysynthetic Languages: Language Teaching and Learning Software for Kanyen’kéha (Mohawk)
Kanyen’kéha (in English, Mohawk) is an Iroquoian language spoken primarily in Eastern Canada (Ontario, Québec). Classified as endangered, it has only a small number of speakers and very few younger
Kawennón:nis: the Wordmaker for Kanyen’kéha
In this paper we describe preliminary work on Kawennón:nis, a verb conjugator for Kanyen'kéha (Ohsweken dialect). The project is the result of a collaboration between Onkwawenna Kentyohkwa
An FST morphological analyzer for the Gitksan language
TLDR
The pre-neural analyzer, tested against interlinear-annotated texts from multiple dialects, achieves coverage of 75-81%, and maintains high precision, while the neural extension improves coverage at the cost of lowered precision.
...
...

References

SHOWING 1-10 OF 83 REFERENCES
Modeling the Noun Morphology of Plains Cree
This paper presents aspects of a computational model of the morphology of Plains Cree based on the technology of finite state transducers (FST). The paper focuses in particular on the modeling of
Semantic and pragmatic functions in Plains Cree syntax
TLDR
This dissertation explores the morphosyntax of the Plains dialect of Cree and the ways in which Semantic, Pragmatic and Syntactic Functions are instantiated, and both case-marking and word order are shown to serve very important functions in Cree syntax, even if not occurring in the forms more familiar from Indo-European languages.
Converting a comprehensive lexical database into a computational model: The case of East Cree verb inflection
In this paper we present a case study of how comprehensive, well-structured, and consistent lexical databases, one indicating the exact inflectional subtype of each word and another exhaustively
Computing with Realizational Morphology
TLDR
It is demonstrated that, in spite of the apparent complexity of Stump's formalism, the system as a whole is no more powerful than a collection of regular relations.
Creating lexical resources for polysynthetic languages—the case of Arapaho
TLDR
The challenges faced by most learners and researchers working with polysynthetic languages, of which Arapaho is an excellent example, are discussed, as well as some currently implemented solutions in creating computer resources for this language, including a lexical database, a morphological parser, and a concordancer.
Nishnaabemwin Reference Grammar
TLDR
This descriptive reference grammar of Nishnaabemwin (Odawa and Eastern Ojibwe) represents the most comprehensive works on an Algonquin language published to date and includes extensive descriptive treatment of phonology, orthography, inflectional morphology, derivational morphology and major structural and functional syntactic categories.
Weighted Finite-State Morphological Analysis of Finnish Compounding with HFST-LEXC
TLDR
This work presents a method for implementing the probabilistic framework as part of the building process of LexC-style morpheme sub-lexicons creating weighted lexical transducers, and demonstrates that it is possible to use non-compound token probabilities to disambiguate the compounding structure.
Axolotl: a Web Accessible Parallel Corpus for Spanish-Nahuatl
TLDR
This paper describes the project called Axolotl which comprises a Spanish-Nahuatl parallel corpus and its search interface, and presents a web search interface that allows to make queries through the whole parallel corpus, capable to retrieve the parallel fragments that contain a word or phrase searched by a user in any of the languages.
Computer Systems for Analysis of Nahuatl
TLDR
Two computer systems that allow us to analyze words written in the Nahuatl language are described, one of which automatically gets prefixes or suffixes of words from a text written in Nahu ATL, and the other is a Nahuacan to Spanish translator and vice versa, which also shows semantic information related to the terms inNahuatl.
Vowels Spaces and Reduction in Plains Cree
The present study is a phonetic description of Plains Cree, an indigenous language spoken in Alberta. This study investigates the acoustic characteristics of the vowel space and instances of
...
...