Charmanteau: Character Embedding Models For Portmanteau Creation
Varun Gangal, Harsh Jhamtani, Graham Neubig, Eduard Hovy, Eric Nyberg
Abstract
Portmanteaus are a word formation phenomenon where two words combine into a new word. We propose character-level neural sequence-to-sequence (S2S) methods for the task of portmanteau generation that are end-to-end-trainable, language independent, and do not explicitly use additional phonetic information. We propose a noisy-channel-style model, which allows for the incorporation of unsupervised word lists, improving performance over a standard source-to-target model. This model is made possible by an exhaustive candidate generation strategy specifically enabled by the features of the portmanteau task. Experiments find our approach superior to a state-of-the-art FST-based baseline with respect to ground truth accuracy and human evaluation.- Anthology ID:
- D17-1315
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2917–2922
- Language:
- URL:
- https://aclanthology.org/D17-1315
- DOI:
- 10.18653/v1/D17-1315
- Cite (ACL):
- Varun Gangal, Harsh Jhamtani, Graham Neubig, Eduard Hovy, and Eric Nyberg. 2017. Charmanteau: Character Embedding Models For Portmanteau Creation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2917–2922, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Charmanteau: Character Embedding Models For Portmanteau Creation (Gangal et al., EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/D17-1315.pdf
- Code
- vgtomahawk/Charmanteau-CamReady