Abstract
This paper presents the first model for time normalization trained on the SCATE corpus. In the SCATE schema, time expressions are annotated as a semantic composition of time entities. This novel schema favors machine learning approaches, as it can be viewed as a semantic parsing task. In this work, we propose a character level multi-output neural network that outperforms previous state-of-the-art built on the TimeML schema. To compare predictions of systems that follow both SCATE and TimeML, we present a new scoring metric for time intervals. We also apply this new metric to carry out a comparative analysis of the annotations of both schemes in the same corpus.- Anthology ID:
- Q18-1025
- Volume:
- Transactions of the Association for Computational Linguistics, Volume 6
- Month:
- Year:
- 2018
- Address:
- Cambridge, MA
- Venue:
- TACL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 343–356
- Language:
- URL:
- https://aclanthology.org/Q18-1025
- DOI:
- 10.1162/tacl_a_00025
- Cite (ACL):
- Egoitz Laparra, Dongfang Xu, and Steven Bethard. 2018. From Characters to Time Intervals: New Paradigms for Evaluation and Neural Parsing of Time Normalizations. Transactions of the Association for Computational Linguistics, 6:343–356.
- Cite (Informal):
- From Characters to Time Intervals: New Paradigms for Evaluation and Neural Parsing of Time Normalizations (Laparra et al., TACL 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/Q18-1025.pdf
- Code
- clulab/timenorm
- Data
- PNT