Abstract
Structured semantic sentence representations such as Abstract Meaning Representations (AMRs) are potentially useful in various NLP tasks. However, the quality of automatic parses can vary greatly and jeopardizes their usefulness. This can be mitigated by models that can accurately rate AMR quality in the absence of costly gold data, allowing us to inform downstream systems about an incorporated parse’s trustworthiness or select among different candidate parses. In this work, we propose to transfer the AMR graph to the domain of images. This allows us to create a simple convolutional neural network (CNN) that imitates a human judge tasked with rating graph quality. Our experiments show that the method can rate quality more accurately than strong baselines, in several quality dimensions. Moreover, the method proves to be efficient and reduces the incurred energy consumption.- Anthology ID:
- 2020.aacl-main.27
- Volume:
- Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing
- Month:
- December
- Year:
- 2020
- Address:
- Suzhou, China
- Venue:
- AACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 235–247
- Language:
- URL:
- https://aclanthology.org/2020.aacl-main.27
- DOI:
- Cite (ACL):
- Juri Opitz. 2020. AMR Quality Rating with a Lightweight CNN. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pages 235–247, Suzhou, China. Association for Computational Linguistics.
- Cite (Informal):
- AMR Quality Rating with a Lightweight CNN (Opitz, AACL 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.aacl-main.27.pdf
- Code
- flipz357/amr-quality-rater