Labeled Morphological Segmentation with Semi-Markov Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910409574842368 |
|---|---|
| author | Cotterell, Ryan Müller, Thomas Fraser, Alexander Schütze, Hinrich |
| author_facet | Cotterell, Ryan Müller, Thomas Fraser, Alexander Schütze, Hinrich |
| contents | We present labeled morphological segmentation, an alternative view of morphological processing that unifies several tasks. From an annotation standpoint, we additionally introduce a new hierarchy of morphotactic tagsets. Finally, we develop \modelname, a discriminative morphological segmentation system that, contrary to previous work, explicitly models morphotactics. We show that \textsc{chipmunk} yields improved performance on three tasks for all six languages: (i) morphological segmentation, (ii) stemming and (iii) morphological tag classification. On morphological segmentation, our method shows absolute improvements of 2--6 points $F_1$ over the baseline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_08997 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Labeled Morphological Segmentation with Semi-Markov Models Cotterell, Ryan Müller, Thomas Fraser, Alexander Schütze, Hinrich Computation and Language We present labeled morphological segmentation, an alternative view of morphological processing that unifies several tasks. From an annotation standpoint, we additionally introduce a new hierarchy of morphotactic tagsets. Finally, we develop \modelname, a discriminative morphological segmentation system that, contrary to previous work, explicitly models morphotactics. We show that \textsc{chipmunk} yields improved performance on three tasks for all six languages: (i) morphological segmentation, (ii) stemming and (iii) morphological tag classification. On morphological segmentation, our method shows absolute improvements of 2--6 points $F_1$ over the baseline. |
| title | Labeled Morphological Segmentation with Semi-Markov Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2404.08997 |