A Language-agnostic Model of Child Language Acquisition
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913476707876864 |
|---|---|
| author | Mahon, Louis Abend, Omri Berger, Uri Demuth, Katherine Johnson, Mark Steedman, Mark |
| author_facet | Mahon, Louis Abend, Omri Berger, Uri Demuth, Katherine Johnson, Mark Steedman, Mark |
| contents | This work reimplements a recent semantic bootstrapping child-language acquisition model, which was originally designed for English, and trains it to learn a new language: Hebrew. The model learns from pairs of utterances and logical forms as meaning representations, and acquires both syntax and word meanings simultaneously. The results show that the model mostly transfers to Hebrew, but that a number of factors, including the richer morphology in Hebrew, makes the learning slower and less robust. This suggests that a clear direction for future work is to enable the model to leverage the similarities between different word forms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_12254 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Language-agnostic Model of Child Language Acquisition Mahon, Louis Abend, Omri Berger, Uri Demuth, Katherine Johnson, Mark Steedman, Mark Computation and Language Artificial Intelligence This work reimplements a recent semantic bootstrapping child-language acquisition model, which was originally designed for English, and trains it to learn a new language: Hebrew. The model learns from pairs of utterances and logical forms as meaning representations, and acquires both syntax and word meanings simultaneously. The results show that the model mostly transfers to Hebrew, but that a number of factors, including the richer morphology in Hebrew, makes the learning slower and less robust. This suggests that a clear direction for future work is to enable the model to leverage the similarities between different word forms. |
| title | A Language-agnostic Model of Child Language Acquisition |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2408.12254 |