AI Bibliography
AI Bibliography |
|
 |
 |
 |
|
Dima, C., de Kok, D., Witte, N., & Hinrichs, E. (2019). No word is an island—a transformation weighting model for semantic composition. Transactions of the Association for Computational Linguistics, 7, 437–451. |
| Resource type: Journal Article BibTeX citation key: Dima2019 View all bibliographic details  |
Categories: Artificial Intelligence, Cognitive Science, Computer Science, Data Sciences, Decision Theory, General, Military Science Subcategories: Big data, Command and control, Decision making, Deep learning, Human decisionmaking, Informatics, Machine learning Creators: de Kok, Dima, Hinrichs, Witte Publisher: Collection: Transactions of the Association for Computational Linguistics |
| Attachments |
| Abstract |
|
Composition models of distributional semantics are used to construct phrase representations from the representations of their words. Composition models are typically situated on two ends of a spectrum. They either have a small number of parameters but compose all phrases in the same way, or they perform word-specific compositions at the cost of a far larger number of parameters. In this paper we propose transformation weighting (TransWeight), a composition model that consistently outperforms existing models on nominal compounds, adjective-noun phrases, and adverb-adjective phrases in English, German, and Dutch. TransWeight drastically reduces the number of parameters needed compared with the best model in the literature by composing similar words in the same way.
|