Abstract
We present a study whose objective is to compare several dependency parsers for English applied to a specialized corpus for building distributional count-based models from syntactic dependencies. One of the particularities of this study is to focus on the concepts of the target domain, which mainly occur in documents as multi-terms and must be aligned with the outputs of the parsers. We compare a set of ten parsers in terms of syntactic triplets but also in terms of distributional neighbors extracted from the models built from these triplets, both with and without an external reference concerning the semantic relations between concepts. We show more particularly that some patterns of proximity between these parsers can be observed across our different evaluations, which could give insights for anticipating the performance of a parser for building distributional models from a given corpus- Anthology ID:
- 2020.computerm-1.4
- Volume:
- Proceedings of the 6th International Workshop on Computational Terminology
- Month:
- May
- Year:
- 2020
- Address:
- Marseille, France
- Venue:
- CompuTerm
- SIG:
- Publisher:
- European Language Resources Association
- Note:
- Pages:
- 26–36
- Language:
- English
- URL:
- https://aclanthology.org/2020.computerm-1.4
- DOI:
- Cite (ACL):
- Pauline Brunet, Olivier Ferret, and Ludovic Tanguy. 2020. Which Dependency Parser to Use for Distributional Semantics in a Specialized Domain?. In Proceedings of the 6th International Workshop on Computational Terminology, pages 26–36, Marseille, France. European Language Resources Association.
- Cite (Informal):
- Which Dependency Parser to Use for Distributional Semantics in a Specialized Domain? (Brunet et al., CompuTerm 2020)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2020.computerm-1.4.pdf