Morfessor-enriched features and multilingual training for canonical morphological segmentation

Forskningsoutput: Kapitel i bok/rapport/konferenshandlingKonferensbidragVetenskapligPeer review

Sammanfattning

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.
Originalspråkengelska
Titel på värdpublikationProceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
RedaktörerGarrett Nicolai, Eleanor Chodroff
Antal sidor8
UtgivningsortStroudsburg
FörlagThe Association for Computational Linguistics
Utgivningsdatumjuni 2022
Sidor144-151
ISBN (elektroniskt)978-1-955917-82-7
DOI
StatusPublicerad - juni 2022
MoE-publikationstypA4 Artikel i en konferenspublikation
EvenemangWorkshop on Computational Research in Phonetics, Phonology, and Morphology - Seattle, Förenta Staterna (USA)
Varaktighet: 14 juli 202214 juli 2022
Konferensnummer: 19

Vetenskapsgrenar

  • 113 Data- och informationsvetenskap

Citera det här