Morfessor-enriched features and multilingual training for canonical morphological segmentation

Aku Rouhe, Stig-Arne Grönroos, Sami Virpioja, Mathias Creutz, Mikko Kurimo

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

14 Lataukset (Pure)

Abstrakti

In our submission to the SIGMORPHON 2022 Shared Task on Morpheme Segmentation, we study whether an unsupervised morphological segmentation method, Morfessor, can help in a supervised setting. Previous research has shown the effectiveness of the approach in semisupervised settings with small amounts of labeled data. The current tasks vary in data size: the amount of word-level annotated training data is much larger, but the amount of sentencelevel annotated training data remains small. Our approach is to pre-segment the input data for a neural sequence-to-sequence model with the unsupervised method. As the unsupervised method can be trained with raw text data, we use Wikipedia to increase the amount of training data. In addition, we train multilingual models for the sentence-level task. The results for the Morfessor-enriched features are mixed, showing benefit for all three sentencelevel tasks but only some of the word-level tasks. The multilingual training yields considerable improvements over the monolingual sentence-level models, but it negates the effect of the enriched features
AlkuperäiskieliEnglanti
OtsikkoProceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
KustantajaAssociation for Computational Linguistics
Sivut144-151
Sivumäärä8
ISBN (painettu)978-1-955917-82-7
DOI - pysyväislinkit
TilaJulkaistu - 2022
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaMeeting of the Special Interest Group on Computational Morphology and Phonology - Seattle, Yhdysvallat
Kesto: 14 heinäk. 202214 heinäk. 2022
Konferenssinumero: 19

Conference

ConferenceMeeting of the Special Interest Group on Computational Morphology and Phonology
LyhennettäSIGMORPHON
Maa/AlueYhdysvallat
KaupunkiSeattle
Ajanjakso14/07/202214/07/2022

Sormenjälki

Sukella tutkimusaiheisiin 'Morfessor-enriched features and multilingual training for canonical morphological segmentation'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä