Danushka Bollegala, James O'neill
We lifted 7 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 |
|---|---|---|
| Bollegala/Meta-Embedding-Framework | canonical | 7 of 7 |
| Function | Status | Where it lives |
|---|---|---|
| avg_baseline | Ran | Bollegala/Meta-Embedding-Framework/baselines.py code served (permissive licence) · get_code("30165c8495ff3bda") |
| cosine | Ran | Bollegala/Meta-Embedding-Framework/wordreps.py code served (permissive licence) · get_code("bf95ee6195f77f93") |
| get_common_words | Ran | Bollegala/Meta-Embedding-Framework/lle.py code served (permissive licence) · get_code("a42b59f39400e8fd") |
| get_embedding | Ran | Bollegala/Meta-Embedding-Framework/wordreps.py code served (permissive licence) · get_code("26ac33d472b8b3d2") |
| get_selected_words | Ran | Bollegala/Meta-Embedding-Framework/lle.py code served (permissive licence) · get_code("bb31c783e139e038") |
| normalize | Ran | Bollegala/Meta-Embedding-Framework/wordreps.py code served (permissive licence) · get_code("e777a9ed755b271e") |
| svd_baseline | Ran | Bollegala/Meta-Embedding-Framework/baselines.py code served (permissive licence) · get_code("ab6b966bf13f1e3d") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Meta-embedding (ME) learning is an emerging approach that attempts to learn more accurate word embeddings given existing (source) word embeddings as the sole input. Due to their ability to incorporate semantics from multiple source embeddings in a compact manner with superior performance, ME learning has gained popularity among practitioners in NLP. To the best of our knowledge, there exist no prior systematic survey on ME learning and this paper attempts to fill this need. We classify ME learning methods according to multiple factors such as whether they (a) operate on static or contextualised embeddings, (b) trained in an unsupervised manner or (c) fine-tuned for a particular task/domain. Moreover, we discuss the limitations of existing ME learning methods and highlight potential future research directions.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2204.11660")
get_code_for_paper("2204.11660")
have("2204.11660")
Connect an agent — have() is free.