Finding the Neural Net: Deep-learning Idiom Type Identification from Distributional Vectors
The present work aims at automatically classifying Italian idiomatic and non-idiomatic phrases with a neural network model under constrains of data scarcity. Results are discussed in comparison with an existing unsupervised model devised for idiom type detection and a similar supervised classifier p...
Đã lưu trong:
| Xuất bản năm: | URI:https://journals.openedition.org/ijcol, |
|---|---|
| Những tác giả chính: | , , |
| Định dạng: | Article ou chapitre numérique |
| Ngôn ngữ: | Anglais |
| Được phát hành: |
IJCoL
2020
|
| Truy cập trực tuyến: | Accès Université d'Orléans et IFPM Accès Université d'Orléans et IFPM |
| Tóm tắt: | The present work aims at automatically classifying Italian idiomatic and non-idiomatic phrases with a neural network model under constrains of data scarcity. Results are discussed in comparison with an existing unsupervised model devised for idiom type detection and a similar supervised classifier previously trained to detect metaphorical bigrams. The experiments suggest that the distributional context of a given phrase is sufficient to carry out idiom type identification to a satisfactory degree, with an increase in performance when input phrases are filtered according to human-elicited idiomaticity ratings collected for the same expressions. Crucially, employing concatenations of single word vectors rather than whole-phrase vectors as training input results in the worst performance for our models, differently from what was previously registered in metaphor detection tasks. |
|---|