We lifted 17 functions out of this paper's own repositories and ran 11 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 |
|---|---|---|
| forest-snow/clime-ui | canonical | 11 of 17 |
| Function | Status | Where it lives |
|---|---|---|
| flatten | Ran | forest-snow/clime-ui/update.py code served (permissive licence) · get_code("20922c79a0929bbf") |
| categorical_accuracy | Ran | forest-snow/clime-ui/model.py code served (permissive licence) · get_code("f0939ff87f1a3402") |
| find_closest | Ran | forest-snow/clime-ui/neighbors.py code served (permissive licence) · get_code("42065f1fcc348923") |
| get_idf | Ran | forest-snow/clime-ui/rank_words.py code served (permissive licence) · get_code("8fb5f65fbdce037b") |
| get_model | Ran | forest-snow/clime-ui/model.py code served (permissive licence) · get_code("51613b0100baa4e7") |
| get_ranking | Ran | forest-snow/clime-ui/rank_words.py code served (permissive licence) · get_code("6bc87aa2db34e64a") |
| load_docs | Ran | forest-snow/clime-ui/utils.py code served (permissive licence) · get_code("c113f6749fd919f4") |
| load_embeddings | Ran | forest-snow/clime-ui/prepare_ui.py code served (permissive licence) · get_code("109cd48e485aae7a") |
| reindex | Ran | forest-snow/clime-ui/update.py code served (permissive licence) · get_code("129f3c77b3077a35") |
| train | Ran | forest-snow/clime-ui/model.py code served (permissive licence) · get_code("80b24aafbca43d95") |
| twod_map | Ran | forest-snow/clime-ui/neighbors.py code served (permissive licence) · get_code("7b2ba76320f84de5") |
| concordance | Not yet run | forest-snow/clime-ui/interface/load.py code served (permissive licence) · get_code("5143afebeee4f04f") |
| load_labels | Not yet run | forest-snow/clime-ui/utils.py code served (permissive licence) · get_code("9ebcf96b972b7a4b") |
| load_vectors | Not yet run | forest-snow/clime-ui/utils.py code served (permissive licence) · get_code("36b86179c80fc3ef") |
| load_vocab | Not yet run | forest-snow/clime-ui/interface/load.py code served (permissive licence) · get_code("357bd3b78248ba9a") |
| rank_vocab | Not yet run | forest-snow/clime-ui/rank_words.py code served (permissive licence) · get_code("de862937f12455fe") |
| read_paths | Not yet run | forest-snow/clime-ui/interface/load.py code served (permissive licence) · get_code("4479c3334d0af517") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Cross-lingual word embeddings transfer knowledge between languages: models trained on high-resource languages can predict in low-resource languages. We introduce CLIME, an interactive system to quickly refine cross-lingual word embeddings for a given classification problem. First, CLIME ranks words by their salience to the downstream task. Then, users mark similarity between keywords and their nearest neighbors in the embedding space. Finally, CLIME updates the embeddings using the annotations. We evaluate CLIME on identifying health-related text in four low-resource languages: Ilocano, Sinhalese, Tigrinya, and Uyghur. Embeddings refined by CLIME capture more nuanced word semantics and have higher test accuracy than the original embeddings. CLIME often improves accuracy faster than an active learning baseline and can be easily combined with active learning to improve results.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1911.03070")
get_code_for_paper("1911.03070")
have("1911.03070")
Connect an agent — have() is free.