ÚFAL LatinPipe at EvaLatin 2024: Morphosyntactic Analysis of Latin
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909212823519232 |
|---|---|
| author | Straka, Milan Straková, Jana Gamba, Federica |
| author_facet | Straka, Milan Straková, Jana Gamba, Federica |
| contents | We present LatinPipe, the winning submission to the EvaLatin 2024 Dependency Parsing shared task. Our system consists of a fine-tuned concatenation of base and large pre-trained LMs, with a dot-product attention head for parsing and softmax classification heads for morphology to jointly learn both dependency parsing and morphological analysis. It is trained by sampling from seven publicly available Latin corpora, utilizing additional harmonization of annotations to achieve a more unified annotation style. Before fine-tuning, we train the system for a few initial epochs with frozen weights. We also add additional local relative contextualization by stacking the BiLSTM layers on top of the Transformer(s). Finally, we ensemble output probability distributions from seven randomly instantiated networks for the final submission. The code is available at https://github.com/ufal/evalatin2024-latinpipe. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_05839 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ÚFAL LatinPipe at EvaLatin 2024: Morphosyntactic Analysis of Latin Straka, Milan Straková, Jana Gamba, Federica Computation and Language We present LatinPipe, the winning submission to the EvaLatin 2024 Dependency Parsing shared task. Our system consists of a fine-tuned concatenation of base and large pre-trained LMs, with a dot-product attention head for parsing and softmax classification heads for morphology to jointly learn both dependency parsing and morphological analysis. It is trained by sampling from seven publicly available Latin corpora, utilizing additional harmonization of annotations to achieve a more unified annotation style. Before fine-tuning, we train the system for a few initial epochs with frozen weights. We also add additional local relative contextualization by stacking the BiLSTM layers on top of the Transformer(s). Finally, we ensemble output probability distributions from seven randomly instantiated networks for the final submission. The code is available at https://github.com/ufal/evalatin2024-latinpipe. |
| title | ÚFAL LatinPipe at EvaLatin 2024: Morphosyntactic Analysis of Latin |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2404.05839 |