The Relative Clauses AMR Parsers Hate Most

Xiulin Yang, Nathan Schneider


Abstract
This paper evaluates how well English Abstract Meaning Representation parsers process an important and frequent kind of Long-Distance Dependency construction, namely, relative clauses (RCs). On two syntactically parsed datasets, we evaluate five AMR parsers at recovering the semantic reentrancies triggered by different syntactic subtypes of relative clauses. Our findings reveal a general difficulty among parsers at predicting such reentrancies, with recall below 64% on the EWT corpus. The sequence-to-sequence models (regardless of whether structural biases were included in training) outperform the compositional model. An analysis by relative clause subtype shows that passive subject RCs are the easiest, and oblique and reduced RCs the most challenging, for AMR parsers.
Anthology ID:
2024.dmr-1.16
Volume:
Proceedings of the Fifth International Workshop on Designing Meaning Representations @ LREC-COLING 2024
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Claire Bonial, Julia Bonn, Jena D. Hwang
Venues:
DMR | WS
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
151–161
Language:
URL:
https://aclanthology.org/2024.dmr-1.16
DOI:
Bibkey:
Cite (ACL):
Xiulin Yang and Nathan Schneider. 2024. The Relative Clauses AMR Parsers Hate Most. In Proceedings of the Fifth International Workshop on Designing Meaning Representations @ LREC-COLING 2024, pages 151–161, Torino, Italia. ELRA and ICCL.
Cite (Informal):
The Relative Clauses AMR Parsers Hate Most (Yang & Schneider, DMR-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.dmr-1.16.pdf