Abstract
Abstract Meaning Representation (AMR) is a sentence-level meaning representation based on predicate argument structure. One of the challenges we find in AMR parsing is to capture the structure of complex sentences which expresses the relation between predicates. Knowing the core part of the sentence structure in advance may be beneficial in such a task. In this paper, we present a list of dependency patterns for English complex sentence constructions designed for AMR parsing. With a dedicated pattern matcher, all occurrences of complex sentence constructions are retrieved from an input sentence. While some of the subordinators have semantic ambiguities, we deal with this problem through training classification models on data derived from AMR and Wikipedia corpus, establishing a new baseline for future works. The developed complex sentence patterns and the corresponding AMR descriptions will be made public.- Anthology ID:
- 2021.starsem-1.20
- Volume:
- Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Lun-Wei Ku, Vivi Nastase, Ivan Vulić
- Venue:
- *SEM
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 212–221
- Language:
- URL:
- https://aclanthology.org/2021.starsem-1.20
- DOI:
- 10.18653/v1/2021.starsem-1.20
- Cite (ACL):
- Yuki Yamamoto, Yuji Matsumoto, and Taro Watanabe. 2021. Dependency Patterns of Complex Sentences and Semantic Disambiguation for Abstract Meaning Representation Parsing. In Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics, pages 212–221, Online. Association for Computational Linguistics.
- Cite (Informal):
- Dependency Patterns of Complex Sentences and Semantic Disambiguation for Abstract Meaning Representation Parsing (Yamamoto et al., *SEM 2021)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2021.starsem-1.20.pdf