The OSU/Facebook Realizer for SRST 2019: Seq2Seq Inflection and Serialized Tree2Tree Linearization

Kartikeya Upasani, David King, Jinfeng Rao, Anusha Balakrishnan, Michael White


Abstract
We describe our exploratory system for the shallow surface realization task, which combines morphological inflection using character sequence-to-sequence models with a baseline linearizer that implements a tree-to-tree model using sequence-to-sequence models on serialized trees. Results for morphological inflection were competitive across languages. Due to time constraints, we could only submit complete results (including linearization) for English. Preliminary linearization results were decent, with a small benefit from reranking to prefer valid output trees, but inadequate control over the words in the output led to poor quality on longer sentences.
Anthology ID:
D19-6309
Volume:
Proceedings of the 2nd Workshop on Multilingual Surface Realisation (MSR 2019)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Simon Mille, Anja Belz, Bernd Bohnet, Yvette Graham, Leo Wanner
Venue:
WS
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
68–74
Language:
URL:
https://aclanthology.org/D19-6309
DOI:
10.18653/v1/D19-6309
Bibkey:
Cite (ACL):
Kartikeya Upasani, David King, Jinfeng Rao, Anusha Balakrishnan, and Michael White. 2019. The OSU/Facebook Realizer for SRST 2019: Seq2Seq Inflection and Serialized Tree2Tree Linearization. In Proceedings of the 2nd Workshop on Multilingual Surface Realisation (MSR 2019), pages 68–74, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
The OSU/Facebook Realizer for SRST 2019: Seq2Seq Inflection and Serialized Tree2Tree Linearization (Upasani et al., 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-6309.pdf