The paper provides a cognitively motivated method for evaluating the inflectional complexity of a language, based on a sample of"raw" inflected word forms processed and learned by a recurrent self-organising neural network with fixed parameter setting. Trainingitems contain no information about either morphological content or structure. This makes the proposed method independent of bothmeta-linguistic issues (e.g. format and expressive power of descriptive rules, manual or automated segmentation of input forms, numberof inflectional classes etc.) and language-specific typological aspects (e.g. word-based, stem-based or template-based morphology).Results are illustrated by contrasting Arabic, English, German, Greek, Italian and Spanish.
Evaluating Inflectional Complexity Crosslinguistically: a Processing Perspective
Marzi C
Primo
;Ferro MSecondo
;Nahli O;Pirrelli VUltimo
2018
Abstract
The paper provides a cognitively motivated method for evaluating the inflectional complexity of a language, based on a sample of"raw" inflected word forms processed and learned by a recurrent self-organising neural network with fixed parameter setting. Trainingitems contain no information about either morphological content or structure. This makes the proposed method independent of bothmeta-linguistic issues (e.g. format and expressive power of descriptive rules, manual or automated segmentation of input forms, numberof inflectional classes etc.) and language-specific typological aspects (e.g. word-based, stem-based or template-based morphology).Results are illustrated by contrasting Arabic, English, German, Greek, Italian and Spanish.| Campo DC | Valore | Lingua |
|---|---|---|
| dc.authority.orgunit | Istituto di linguistica computazionale "Antonio Zampolli" - ILC | en |
| dc.authority.people | Marzi C | en |
| dc.authority.people | Ferro M | en |
| dc.authority.people | Nahli O | en |
| dc.authority.people | Belik P | en |
| dc.authority.people | Bompolas S | en |
| dc.authority.people | Pirrelli V | en |
| dc.collection.id.s | 71c7200a-7c5f-4e83-8d57-d3d2ba88f40d | * |
| dc.collection.name | 04.01 Contributo in Atti di convegno | * |
| dc.contributor.appartenenza | Istituto di linguistica computazionale "Antonio Zampolli" - ILC | * |
| dc.contributor.appartenenza.mi | 918 | * |
| dc.date.accessioned | 2024/02/15 18:52:21 | - |
| dc.date.available | 2024/02/15 18:52:21 | - |
| dc.date.firstsubmission | 2024/09/26 16:42:05 | * |
| dc.date.issued | 2018 | - |
| dc.date.submission | 2024/09/26 16:42:05 | * |
| dc.description.abstracteng | The paper provides a cognitively motivated method for evaluating the inflectional complexity of a language, based on a sample of"raw" inflected word forms processed and learned by a recurrent self-organising neural network with fixed parameter setting. Trainingitems contain no information about either morphological content or structure. This makes the proposed method independent of bothmeta-linguistic issues (e.g. format and expressive power of descriptive rules, manual or automated segmentation of input forms, numberof inflectional classes etc.) and language-specific typological aspects (e.g. word-based, stem-based or template-based morphology).Results are illustrated by contrasting Arabic, English, German, Greek, Italian and Spanish. | - |
| dc.description.affiliations | Institute for Computational Linguistics-CNR; Universitat Politècnica de Valencia; University of Patras | - |
| dc.description.allpeople | Marzi, C; Ferro, M; Nahli, O; Belik, P; Bompolas, S; Pirrelli, V | - |
| dc.description.allpeopleoriginal | Marzi, C.; Ferro, M.; Nahli, O.; Belik, P.; Bompolas, S.; Pirrelli, V. | en |
| dc.description.fulltext | none | en |
| dc.description.numberofauthors | 6 | - |
| dc.identifier.isbn | 979-10-95546-00-9 | en |
| dc.identifier.uri | https://hdl.handle.net/20.500.14243/349950 | - |
| dc.identifier.url | http://www.lrec-conf.org/proceedings/lrec2018/summaries/745.html | en |
| dc.language.iso | eng | en |
| dc.miur.last.status.update | 2024-09-25T13:10:20Z | * |
| dc.publisher.country | FRA | en |
| dc.publisher.name | European language resources association (ELRA) | en |
| dc.publisher.place | Paris | en |
| dc.relation.alleditors | N. Calzolari, K. Choukri, C. Cieri, T. Declerck, S. Goggi, K. Hasida, H. Isahara, B. Maegaard, J. Mariani, H. Mazo, A. Moreno, J. Odijk, S. Piperidis & T. Tokunaga | en |
| dc.relation.conferencedate | 7-12/05/2018 | en |
| dc.relation.conferencename | Eleventh International Conference on Language Resources and Evaluation (LREC 2018) | en |
| dc.relation.conferenceplace | Miyazaki, Japan | en |
| dc.relation.firstpage | 3860 | en |
| dc.relation.ispartofbook | Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018) | en |
| dc.relation.lastpage | 3866 | en |
| dc.relation.medium | ELETTRONICO | en |
| dc.relation.numberofpages | 7 | en |
| dc.subject.keywordseng | paradigm-based morphology | - |
| dc.subject.keywordseng | inflectional complexity | - |
| dc.subject.keywordseng | prediction-based processing | - |
| dc.subject.keywordseng | recurrent self-organising networks | - |
| dc.subject.keywordseng | Statistical And Machine Learning Methods | - |
| dc.subject.keywordseng | Language Modelling | - |
| dc.subject.singlekeyword | paradigm-based morphology | * |
| dc.subject.singlekeyword | inflectional complexity | * |
| dc.subject.singlekeyword | prediction-based processing | * |
| dc.subject.singlekeyword | recurrent self-organising networks | * |
| dc.subject.singlekeyword | Statistical And Machine Learning Methods | * |
| dc.subject.singlekeyword | Language Modelling | * |
| dc.title | Evaluating Inflectional Complexity Crosslinguistically: a Processing Perspective | en |
| dc.type.driver | info:eu-repo/semantics/conferenceObject | - |
| dc.type.full | 04 Contributo in convegno::04.01 Contributo in Atti di convegno | it |
| dc.type.miur | 273 | - |
| dc.type.referee | Esperti anonimi | en |
| dc.ugov.descaux1 | 388016 | - |
| iris.orcid.lastModifiedDate | 2024/11/29 17:55:36 | * |
| iris.orcid.lastModifiedMillisecond | 1732899336027 | * |
| iris.sitodocente.maxattempts | 1 | - |
| Appare nelle tipologie: | 04.01 Contributo in Atti di convegno | |
File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
