Eesti keele püsiühendid arvutilingvistikas: miks ja kuidas

Muischnek, Kadri; Kaalep, Heiki-Jaan

doi:10.5128/erya5.10

Cited by 4 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Table 1 shows that in the spoken corpus, vaja clearly dominates. In the data drawn from the written corpus, the proportion of tarvis and vaja clauses is equal; however, vaja is reported to be used approximately 3.5 times more frequently than tarvis in contemporary written Estonian (Kaalep & Muischnek 2002). Hence, the sample is not representative in terms of the balance in usage of the modal adverbs, tarvis and vaja , but it was necessary to include a critical amount of clauses with tarvis in order to test whether the choice of adverb had an influence on experiencer marking.…”

Section: Methodsmentioning

confidence: 97%

Who needs it? Variation in experiencer marking in Estonian ‘need’-constructions

Lindström

Vihman

2017

J. Ling.

View full text Add to dashboard Cite

In this paper, we tackle the twin issues of obligatoriness of semantic arguments and variation in their expression through a study of Estonian constructions denoting need. The variation under investigation consists in the choice of case-marking, between adessive and allative case, as well as the option to omit the oblique argument. We extracted and coded ‘need’-constructions from spoken and written corpora and used non-parametric classification methods for analysis. We found high rates of oblique experiencer omission in these constructions (nearly 60% across corpora). The most important predictors of overt expression of the experiencer in our models were participant-internal modality and the presence of nominal complements, meaning that both semantic and syntactic factors are relevant. The choice between two overt cases is affected by person, complement type, and referential distance. Topical experiencer arguments do not show the subject-like tendency to be omitted more often, but they are more likely to be marked with adessive case, suggesting that adessive is more grammaticalised as a structural, non-nominative, argument-marking case than the more semantic allative case. Our findings show that oblique, semantic arguments may be frequently omitted, and both semantic and syntactic factors may affect variation in case-marking.

show abstract

Section: Methodsmentioning

confidence: 97%

Who needs it? Variation in experiencer marking in Estonian ‘need’-constructions

Lindström

Vihman

2017

J. Ling.

View full text Add to dashboard Cite

show abstract

“…Eestikeelse ülevaate püsiühendite probleemistikust arvutilingvistikas annab Kadri Muischneki ja Heiki-Jaan Kaalepi artikkel "Eesti keele püsiühendid arvutilingvistikas: miks ja kuidas" (Muischnek, Kaalep 2009).…”

Section: Sarnane Uurimistöö Eesti Keele Ja Ka Teiste Keelte Alalunclassified

Ühendverbid eesti keele pindsüntaktilises analüüsis

Muischnek

Müürisep

Puolakainen

2014

ERYa

Self Cite

View full text Add to dashboard Cite

Ülevaade. Artikkel käsitleb ühendverbide tuvastamist eesti keele automaatse pindsüntaktilise analüüsi käigus. Ühendverbide äratundmine on vajalik lause täpsemaks süntaktiliseks analüüsiks, sest lause osaliste süntaktilised funktsioonid, semantilised rollid ja nende keelendamine sõltub sellest, milline on lause keskmeks olev predikaatverb, sh sellest, kas predikaatverb on lihtverb või ühendverb. Ühendverbide tuvastamiseks rakendatakse kahte strateegiat: leksikonipõhist ja reeglipõhist. Viimane tähendab seda, et osa korrapäraseid produktiivselt kombineeruvaid ühendverbe pannakse kokku reeglite abil. Artiklis kirjeldatakse kahte eksperimenti: esialgse ja täiustatud ühendverbide tuvastamise käiku. Täiustatud süsteemi tulemus on päris hea, saavutades saagise 97,4% ja täpsuse 96,6%.* Võtmesõnad: arvutilingvistika, püsiühendite tuvastamine, eesti keel * Artikli valmimist on toetanud Euroopa Regionaalarengufond Eesti Arvutiteaduse Tippkeskuse kaudu ning Haridusja Teadusministeerium institutsionaalse uurimistoetuse IUT 20-56 "Eesti keele arvutimudelid" kaudu.

show abstract

“…[10]There is no frequency data available for Võro, but if we take the data from standard written Estonian as a rough guide, the corresponding verbs are ranked as the first ( olema ), third ( tulema ), fifth ( tegema ) and eleventh ( nägema ) most frequent verb lexemes (Kaalep & Muischnek 2002). …”

mentioning

confidence: 99%

Covert systematicity in a distributionally complex system

Baerman

2013

J. Ling.

View full text Add to dashboard Cite

Current thinking on inflection classes views them as organized networks rather than random assemblages of allomorphs (Carstairs-McCarthy 1994, Malouf & Ackerman 2010, Müller 2007), but we still find systems which appear to lack any visible implicative structure. A particularly striking example comes from Võro (a variety of South Estonian). Its system of verbal inflectional suffixes is formally simple but distributionally complex: although there are never more than three allomorphs in competition, nearly two dozen inflectional patterns emerge through rampant crossclassification of the allomorphs. Allomorph choice in one part of the paradigm thus fails to constrain allomorph choice in the rest, so it looks as if the paradigms would have to be memorized en masse. The key to these patterns lies outside the system of suffixation itself, in the more conventional formal complexity of stem alternations and their paradigmatic patterning. The computationally implemented analysis presented here provides a model of inflection in which the implicational network of phonological, morphophonological and morphological conditions on formal realization are unified in a single representation.

show abstract

Eesti keele püsiühendid arvutilingvistikas: miks ja kuidas

Cited by 4 publications

References 1 publication

Who needs it? Variation in experiencer marking in Estonian ‘need’-constructions

Who needs it? Variation in experiencer marking in Estonian ‘need’-constructions

Ühendverbid eesti keele pindsüntaktilises analüüsis

Covert systematicity in a distributionally complex system

Contact Info

Product

Resources

About