Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2311.03963 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918102160113664 |
|---|---|
| author | Uduehi, Oseremen O. Bunescu, Razvan C. |
| author_facet | Uduehi, Oseremen O. Bunescu, Razvan C. |
| contents | We propose a metaphor detection architecture that is structured around two main modules: an expectation component that estimates representations of literal word expectations given a context, and a realization component that computes representations of actual word meanings in context. The overall architecture is trained to learn expectation-realization (ER) patterns that characterize metaphorical uses of words. When evaluated on three metaphor datasets for within distribution, out of distribution, and novel metaphor generalization, the proposed method is shown to obtain results that are competitive or better than state-of-the art. Further increases in metaphor detection accuracy are obtained through ensembling of ER models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_03963 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | An Expectation-Realization Model for Metaphor Detection Uduehi, Oseremen O. Bunescu, Razvan C. Computation and Language Artificial Intelligence We propose a metaphor detection architecture that is structured around two main modules: an expectation component that estimates representations of literal word expectations given a context, and a realization component that computes representations of actual word meanings in context. The overall architecture is trained to learn expectation-realization (ER) patterns that characterize metaphorical uses of words. When evaluated on three metaphor datasets for within distribution, out of distribution, and novel metaphor generalization, the proposed method is shown to obtain results that are competitive or better than state-of-the art. Further increases in metaphor detection accuracy are obtained through ensembling of ER models. |
| title | An Expectation-Realization Model for Metaphor Detection |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2311.03963 |