BinaryAlign: Word Alignment as Binary Sequence Labeling
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917725432971264 |
|---|---|
| author | Latouche, Gaetan Lopez Carbonneau, Marc-André Swanson, Ben |
| author_facet | Latouche, Gaetan Lopez Carbonneau, Marc-André Swanson, Ben |
| contents | Real world deployments of word alignment are almost certain to cover both high and low resource languages. However, the state-of-the-art for this task recommends a different model class depending on the availability of gold alignment training data for a particular language pair. We propose BinaryAlign, a novel word alignment technique based on binary sequence labeling that outperforms existing approaches in both scenarios, offering a unifying approach to the task. Additionally, we vary the specific choice of multilingual foundation model, perform stratified error analysis over alignment error type, and explore the performance of BinaryAlign on non-English language pairs. We make our source code publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_12881 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BinaryAlign: Word Alignment as Binary Sequence Labeling Latouche, Gaetan Lopez Carbonneau, Marc-André Swanson, Ben Computation and Language Artificial Intelligence Real world deployments of word alignment are almost certain to cover both high and low resource languages. However, the state-of-the-art for this task recommends a different model class depending on the availability of gold alignment training data for a particular language pair. We propose BinaryAlign, a novel word alignment technique based on binary sequence labeling that outperforms existing approaches in both scenarios, offering a unifying approach to the task. Additionally, we vary the specific choice of multilingual foundation model, perform stratified error analysis over alignment error type, and explore the performance of BinaryAlign on non-English language pairs. We make our source code publicly available. |
| title | BinaryAlign: Word Alignment as Binary Sequence Labeling |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2407.12881 |