Abstract
Matching genre in training and test data has been shown to improve dependency parsing. However, it is not clear whether the used methods capture only the genre feature. We hypothesize that successful transfer may also depend on topic similarity. Using topic modelling, we assess whether cross-genre transfer in dependency parsing is stable with respect to topic distribution. We show that LAS scores in cross-genre transfer within and across treebanks typically align with topic distances. This indicates that topic is an important explanatory factor for genre transfer.- Anthology ID:
- 2024.lrec-main.1211
- Volume:
- Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
- Venues:
- LREC | COLING
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 13879–13884
- Language:
- URL:
- https://aclanthology.org/2024.lrec-main.1211
- DOI:
- Cite (ACL):
- Vera Danilova and Sara Stymne. 2024. Relation between Cross-Genre and Cross-Topic Transfer in Dependency Parsing. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 13879–13884, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- Relation between Cross-Genre and Cross-Topic Transfer in Dependency Parsing (Danilova & Stymne, LREC-COLING 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2024.lrec-main.1211.pdf