Abstract
This paper presents the solution proposed by DTeam in the VarDial 2019 Evaluation Campaign for the Moldavian vs. Romanian cross-topic identification task. The solution proposed is a Support Vector Machines (SVM) ensemble composed of a two character-level neural networks. The first network is a skip-gram classification model formed of an embedding layer, three convolutional layers and two fully-connected layers. The second network has a similar architecture, but is trained using the triplet loss function.- Anthology ID:
- W19-1422
- Volume:
- Proceedings of the Sixth Workshop on NLP for Similar Languages, Varieties and Dialects
- Month:
- June
- Year:
- 2019
- Address:
- Ann Arbor, Michigan
- Editors:
- Marcos Zampieri, Preslav Nakov, Shervin Malmasi, Nikola Ljubešić, Jörg Tiedemann, Ahmed Ali
- Venue:
- VarDial
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 202–208
- Language:
- URL:
- https://aclanthology.org/W19-1422
- DOI:
- 10.18653/v1/W19-1422
- Cite (ACL):
- Diana Tudoreanu. 2019. DTeam @ VarDial 2019: Ensemble based on skip-gram and triplet loss neural networks for Moldavian vs. Romanian cross-dialect topic identification. In Proceedings of the Sixth Workshop on NLP for Similar Languages, Varieties and Dialects, pages 202–208, Ann Arbor, Michigan. Association for Computational Linguistics.
- Cite (Informal):
- DTeam @ VarDial 2019: Ensemble based on skip-gram and triplet loss neural networks for Moldavian vs. Romanian cross-dialect topic identification (Tudoreanu, VarDial 2019)
- PDF:
- https://preview.aclanthology.org/corrections-2024-07/W19-1422.pdf
- Data
- MOROCO