Abstract
We present new results for the problem of sequence metaphor labeling, using the recently developed Visibility Embeddings. We show that concatenating such embeddings to the input of a BiLSTM obtains consistent and significant improvements at almost no cost, and we present further improved results when visibility embeddings are combined with BERT.- Anthology ID:
- 2021.starsem-1.21
- Volume:
- Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Venue:
- *SEM
- SIG:
- SIGSEM
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 222–228
- Language:
- URL:
- https://aclanthology.org/2021.starsem-1.21
- DOI:
- 10.18653/v1/2021.starsem-1.21
- Cite (ACL):
- Gitit Kehat and James Pustejovsky. 2021. Neural Metaphor Detection with Visibility Embeddings. In Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics, pages 222–228, Online. Association for Computational Linguistics.
- Cite (Informal):
- Neural Metaphor Detection with Visibility Embeddings (Kehat & Pustejovsky, *SEM 2021)
- PDF:
- https://preview.aclanthology.org/author-url/2021.starsem-1.21.pdf
- Data
- Visual Genome