Utilizing Subword Entities in Character-Level Sequence-to-Sequence Lemmatization Models

Nasser Zalmout, Nizar Habash


Abstract
In this paper we present a character-level sequence-to-sequence lemmatization model, utilizing several subword features in multiple configurations. In addition to generic n-gram embeddings (using FastText), we experiment with concatenative (stems) and templatic (roots and patterns) morphological subwords. We present several architectures that embed these features directly at the encoder side, or learn them jointly at the decoder side with a multitask learning architecture. The results indicate that using the generic n-gram embeddings (through FastText) outperform the other linguistically-driven subwords. We use Modern Standard Arabic and Egyptian Arabic as test cases, with up to 22% and 13% relative error reduction, respectively, from a strong baseline. An error analysis shows that our best system is even able to handle word/lemma pairs that are both unseen in the training data.
Anthology ID:
2020.coling-main.412
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
4676–4682
Language:
URL:
https://aclanthology.org/2020.coling-main.412
DOI:
10.18653/v1/2020.coling-main.412
Bibkey:
Cite (ACL):
Nasser Zalmout and Nizar Habash. 2020. Utilizing Subword Entities in Character-Level Sequence-to-Sequence Lemmatization Models. In Proceedings of the 28th International Conference on Computational Linguistics, pages 4676–4682, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Utilizing Subword Entities in Character-Level Sequence-to-Sequence Lemmatization Models (Zalmout & Habash, COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.412.pdf