Andy Way, Steinþór Steingrímsson, Hrafn Loftsson
We lifted 10 functions out of this paper's own repositories and ran 8 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| steinst/sentalign | — | 8 of 10 |
| Function | Status | Where it lives |
|---|---|---|
| add_nulls | Ran | steinst/sentalign/align_anchors.py code served (permissive licence) · get_code("a96e7e2f0548f8b5") |
| check_for_nulls | Ran | steinst/sentalign/align_anchors.py code served (permissive licence) · get_code("493838232d77d877") |
| concat_strings | Ran | steinst/sentalign/align_anchors.py code served (permissive licence) · get_code("bb9416f36b47caaf") |
| create_combinations_from_concatenations | Ran | steinst/sentalign/align_anchors.py code served (permissive licence) · get_code("6b9787c8d7cf5c19") |
| create_concats | Ran | steinst/sentalign/align_anchors.py code served (permissive licence) · get_code("b674d206c22a46ac") |
| get_highest_scoring_pairs | Ran | steinst/sentalign/align_anchors.py code served (permissive licence) · get_code("fc921754526f6839") |
| get_labse_score | Ran | steinst/sentalign/align_anchors.py code served (permissive licence) · get_code("3524d3d98293aa63") |
| reevaluate_path | Ran | steinst/sentalign/align_anchors.py code served (permissive licence) · get_code("c7ebf2f9d86ba79d") |
| align_anchors | Not yet run | steinst/sentalign/align_anchors.py code served (permissive licence) · get_code("5c4014d6f76d370c") |
| fill_null_aligns | Not yet run | steinst/sentalign/align_anchors.py code served (permissive licence) · get_code("8358c8ed0b6c07e5") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We present SentAlign, an accurate sentence alignment tool designed to handle very large parallel document pairs. Given user-defined parameters, the alignment algorithm evaluates all possible alignment paths in fairly large documents of thousands of sentences and uses a divide-and-conquer approach to align documents containing tens of thousands of sentences. The scoring function is based on LaBSE bilingual sentence representations. SentAlign outperforms five other sentence alignment tools when evaluated on two different evaluation sets, German-French and English-Icelandic, and on a downstream machine translation task.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2311.08982")
get_code_for_paper("2311.08982")
have("2311.08982")
Connect an agent — have() is free.