Abstract
This paper presents a statistical model to predict Japanese word order in the double object constructions. We employed a Bayesian linear mixed model with manually annotated predicate-argument structure data. The findings from the refined corpus analysis confirmed the effects of information status of an NP as ‘givennew ordering’ in addition to the effects of ‘long-before-short’ as a tendency of the general Japanese word order.- Anthology ID:
- W18-2805
- Volume:
- Proceedings of the Eight Workshop on Cognitive Aspects of Computational Language Learning and Processing
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne
- Venue:
- CogACLL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 36–40
- Language:
- URL:
- https://aclanthology.org/W18-2805
- DOI:
- 10.18653/v1/W18-2805
- Cite (ACL):
- Masayuki Asahara, Satoshi Nambu, and Shin-Ichiro Sano. 2018. Predicting Japanese Word Order in Double Object Constructions. In Proceedings of the Eight Workshop on Cognitive Aspects of Computational Language Learning and Processing, pages 36–40, Melbourne. Association for Computational Linguistics.
- Cite (Informal):
- Predicting Japanese Word Order in Double Object Constructions (Asahara et al., CogACLL 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/W18-2805.pdf