Compositional Morpheme Embeddings with Affixes as Functions and Stems as Arguments

Daniel Edmiston, Karl Stratos


Abstract
This work introduces a novel, linguistically motivated architecture for composing morphemes to derive word embeddings. The principal novelty in the work is to treat stems as vectors and affixes as functions over vectors. In this way, our model’s architecture more closely resembles the compositionality of morphemes in natural language. Such a model stands in opposition to models which treat morphemes uniformly, making no distinction between stem and affix. We run this new architecture on a dependency parsing task in Korean—a language rich in derivational morphology—and compare it against a lexical baseline,along with other sub-word architectures. StAffNet, the name of our architecture, shows competitive performance with the state-of-the-art on this task.
Anthology ID:
W18-2901
Volume:
Proceedings of the Workshop on the Relevance of Linguistic Structure in Neural Architectures for NLP
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Georgiana Dinu, Miguel Ballesteros, Avirup Sil, Sam Bowman, Wael Hamza, Anders Sogaard, Tahira Naseem, Yoav Goldberg
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–5
Language:
URL:
https://aclanthology.org/W18-2901
DOI:
10.18653/v1/W18-2901
Bibkey:
Cite (ACL):
Daniel Edmiston and Karl Stratos. 2018. Compositional Morpheme Embeddings with Affixes as Functions and Stems as Arguments. In Proceedings of the Workshop on the Relevance of Linguistic Structure in Neural Architectures for NLP, pages 1–5, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Compositional Morpheme Embeddings with Affixes as Functions and Stems as Arguments (Edmiston & Stratos, ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-2901.pdf