The Reading Machine: A Versatile Framework for Studying Incremental Parsing Strategies

Franck Dary, Alexis Nasr


Abstract
The Reading Machine, is a parsing framework that takes as input raw text and performs six standard nlp tasks: tokenization, pos tagging, morphological analysis, lemmatization, dependency parsing and sentence segmentation. It is built upon Transition Based Parsing, and allows to implement a large number of parsing configurations, among which a fully incremental one. Three case studies are presented to highlight the versatility of the framework. The first one explores whether an incremental parser is able to take into account top-down dependencies (i.e. the influence of high level decisions on low level ones), the second compares the performances of an incremental and a pipe-line architecture and the third quantifies the impact of the right context on the predictions made by an incremental parser.
Anthology ID:
2021.iwpt-1.3
Volume:
Proceedings of the 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies (IWPT 2021)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP | IWPT
SIG:
SIGPARSE
Publisher:
Association for Computational Linguistics
Note:
Pages:
26–37
Language:
URL:
https://aclanthology.org/2021.iwpt-1.3
DOI:
10.18653/v1/2021.iwpt-1.3
Bibkey:
Cite (ACL):
Franck Dary and Alexis Nasr. 2021. The Reading Machine: A Versatile Framework for Studying Incremental Parsing Strategies. In Proceedings of the 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies (IWPT 2021), pages 26–37, Online. Association for Computational Linguistics.
Cite (Informal):
The Reading Machine: A Versatile Framework for Studying Incremental Parsing Strategies (Dary & Nasr, IWPT 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.iwpt-1.3.pdf