Abstract
Abstract In this work, we present a phenomenon-oriented comparative analysis of the two dominant approaches in English Resource Semantic (ERS) parsing: classic, knowledge-intensive and neural, data-intensive models. To reflect state-of-the-art neural NLP technologies, a factorization-based parser is introduced that can produce Elementary Dependency Structures much more accurately than previous data-driven parsers. We conduct a suite of tests for different linguistic phenomena to analyze the grammatical competence of different parsers, where we show that, despite comparable performance overall, knowledge- and data-intensive models produce different types of errors, in a way that can be explained by their theoretical properties. This analysis is beneficial to in-depth evaluation of several representative parsing techniques and leads to new directions for parser development.- Anthology ID:
- 2021.cl-1.3
- Volume:
- Computational Linguistics, Volume 47, Issue 1 - March 2021
- Month:
- March
- Year:
- 2021
- Address:
- Cambridge, MA
- Venue:
- CL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 43–68
- Language:
- URL:
- https://aclanthology.org/2021.cl-1.3
- DOI:
- 10.1162/coli_a_00395
- Cite (ACL):
- Junjie Cao, Zi Lin, Weiwei Sun, and Xiaojun Wan. 2021. Comparing Knowledge-Intensive and Data-Intensive Models for English Resource Semantic Parsing. Computational Linguistics, 47(1):43–68.
- Cite (Informal):
- Comparing Knowledge-Intensive and Data-Intensive Models for English Resource Semantic Parsing (Cao et al., CL 2021)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2021.cl-1.3.pdf