Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2410.18225 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929556654391296 |
|---|---|
| author | Howitt, Katherine Nair, Sathvik Dods, Allison Hopkins, Robert Melvin |
| author_facet | Howitt, Katherine Nair, Sathvik Dods, Allison Hopkins, Robert Melvin |
| contents | Humans develop their grammars by making structural generalizations from finite input. We ask how filler-gap dependencies, which share a structural generalization despite diverse surface forms, might arise from the input. We explicitly control the input to a neural language model (NLM) to uncover whether the model posits a shared representation for filler-gap dependencies. We show that while NLMs do have success differentiating grammatical from ungrammatical filler-gap dependencies, they rely on superficial properties of the input, rather than on a shared generalization. Our work highlights the need for specific linguistic inductive biases to model language acquisition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_18225 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generalizations across filler-gap dependencies in neural language models Howitt, Katherine Nair, Sathvik Dods, Allison Hopkins, Robert Melvin Computation and Language Humans develop their grammars by making structural generalizations from finite input. We ask how filler-gap dependencies, which share a structural generalization despite diverse surface forms, might arise from the input. We explicitly control the input to a neural language model (NLM) to uncover whether the model posits a shared representation for filler-gap dependencies. We show that while NLMs do have success differentiating grammatical from ungrammatical filler-gap dependencies, they rely on superficial properties of the input, rather than on a shared generalization. Our work highlights the need for specific linguistic inductive biases to model language acquisition. |
| title | Generalizations across filler-gap dependencies in neural language models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2410.18225 |