Human and Automatic Interpretation of Romanian Noun Compounds
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910361831079936 |
|---|---|
| author | Marinescu, Ioana Fellbaum, Christiane |
| author_facet | Marinescu, Ioana Fellbaum, Christiane |
| contents | Determining the intended, context-dependent meanings of noun compounds like "shoe sale" and "fire sale" remains a challenge for NLP. Previous work has relied on inventories of semantic relations that capture the different meanings between compound members. Focusing on Romanian compounds, whose morphosyntax differs from that of their English counterparts, we propose a new set of relations and test it with human annotators and a neural net classifier. Results show an alignment of the network's predictions and human judgments, even where the human agreement rate is low. Agreement tracks with the frequency of the selected relations, regardless of structural differences. However, the most frequently selected relation was none of the sixteen labeled semantic relations, indicating the need for a better relation inventory. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_06360 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Human and Automatic Interpretation of Romanian Noun Compounds Marinescu, Ioana Fellbaum, Christiane Computation and Language Artificial Intelligence Determining the intended, context-dependent meanings of noun compounds like "shoe sale" and "fire sale" remains a challenge for NLP. Previous work has relied on inventories of semantic relations that capture the different meanings between compound members. Focusing on Romanian compounds, whose morphosyntax differs from that of their English counterparts, we propose a new set of relations and test it with human annotators and a neural net classifier. Results show an alignment of the network's predictions and human judgments, even where the human agreement rate is low. Agreement tracks with the frequency of the selected relations, regardless of structural differences. However, the most frequently selected relation was none of the sixteen labeled semantic relations, indicating the need for a better relation inventory. |
| title | Human and Automatic Interpretation of Romanian Noun Compounds |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2403.06360 |