Jonathan May, Zhao Zhang, Thamme Gowda, Chris Mattmann
We lifted 8 functions out of this paper's own repositories and ran 7 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 |
|---|---|---|
| thammegowda/mtdata | canonical | 4 of 4 |
| isi-nlp/nlcodec | canonical | 3 of 4 |
| Function | Status | Where it lives |
|---|---|---|
| best_dtype | Ran | isi-nlp/nlcodec/nlcodec/db/core.py code served (permissive licence) · get_code("e54b92783a8ddbc7") |
| clean | Ran | thammegowda/mtdata/mtdata/sgm.py code served (permissive licence) · get_code("c6cdc9376ddcef6a") |
| detect_extension | Ran | thammegowda/mtdata/mtdata/parser.py code served (permissive licence) · get_code("280ccbb1b0e4fbd4") |
| make_n_grams | Ran | isi-nlp/nlcodec/nlcodec/utils.py code served (permissive licence) · get_code("b6e62eee451f9729") |
| part_path_pads | Ran | isi-nlp/nlcodec/nlcodec/db/core.py code served (permissive licence) · get_code("f99e72c2983a154b") |
| right_replace | Ran | thammegowda/mtdata/mtdata/cache.py code served (permissive licence) · get_code("ed8430505d05f010") |
| rreplace | Ran | thammegowda/mtdata/mtdata/data.py code served (permissive licence) · get_code("ed598e786b62e136") |
| subsequent_mask | Not yet run | isi-nlp/nlcodec/nlcodec/db/batch.py code served (permissive licence) · get_code("391870b445058aab") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
While there are more than 7000 languages in the world, most translation research efforts have targeted a few high resource languages. Commercial translation systems support only one hundred languages or fewer, and do not make these models available for transfer to low resource languages. In this work, we present useful tools for machine translation research: MTDATA, NLCODEC, and RTG. We demonstrate their usefulness by creating a multilingual neural machine translation model capable of translating from 500 source languages to English. We make this multilingual model readily downloadable and usable as a service, or as a parent model for transfer-learning to even lower-resource languages. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2104.00290")
get_code_for_paper("2104.00290")
have("2104.00290")
Connect an agent — have() is free.