Abstract
Mathematical statements written in natural language are usually composed of two different modalities: mathematical elements and natural language. These two modalities have several distinct linguistic and semantic properties. State-of-the-art representation techniques have demonstrated an inability in capturing such an entangled style of discourse. In this work, we propose STAR, a model that uses cross-modal attention to learn how to represent mathematical text for the task of Natural Language Premise Selection. This task uses conjectures written in both natural and mathematical language to recommend premises that most likely will be relevant to prove a particular statement. We found that STAR not only outperforms baselines that do not distinguish between natural language and mathematical elements, but it also achieves better performance than state-of-the-art models.- Anthology ID:
- 2021.eacl-main.282
- Volume:
- Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
- Month:
- April
- Year:
- 2021
- Address:
- Online
- Editors:
- Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3234–3243
- Language:
- URL:
- https://aclanthology.org/2021.eacl-main.282
- DOI:
- 10.18653/v1/2021.eacl-main.282
- Cite (ACL):
- Deborah Ferreira and André Freitas. 2021. STAR: Cross-modal [STA]tement [R]epresentation for selecting relevant mathematical premises. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3234–3243, Online. Association for Computational Linguistics.
- Cite (Informal):
- STAR: Cross-modal [STA]tement [R]epresentation for selecting relevant mathematical premises (Ferreira & Freitas, EACL 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2021.eacl-main.282.pdf