We lifted 8 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 |
|---|---|---|
| kimiyoung/transfer | canonical | 8 of 8 |
| Function | Status | Where it lives |
|---|---|---|
| create_char_index | Ran | kimiyoung/transfer/twitter_pos.py code served (permissive licence) · get_code("48b2627eed59512d") |
| create_sample_index | Ran | kimiyoung/transfer/sample.py code served (permissive licence) · get_code("5a642cc01d51efa4") |
| create_word_index | Ran | kimiyoung/transfer/genia.py code served (permissive licence) · get_code("01ca0df692aec1ec") |
| label_decode | Ran | kimiyoung/transfer/chunking.py code served (permissive licence) · get_code("653e0ef660a7a66d") |
| process | Ran | kimiyoung/transfer/chunking.py code served (permissive licence) · get_code("a00ea359508e75a1") |
| process_labels | Ran | kimiyoung/transfer/chunking.py code served (permissive licence) · get_code("bb32c25f9db18c4f") |
| sample_arrays | Ran | kimiyoung/transfer/sample.py code served (permissive licence) · get_code("e1f2eaa16b279dac") |
| trans_label | Ran | kimiyoung/transfer/genia.py code served (permissive licence) · get_code("43d5b6a692a442f0") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Recent papers have shown that neural networks obtain state-of-the-art performance on several different sequence tagging tasks. One appealing property of such systems is their generality, as excellent performance can be achieved with a unified architecture and without task-specific feature engineering. However, it is unclear if such systems can be used for tasks without large amounts of training data. In this paper we explore the problem of transfer learning for neural sequence taggers, where a source task with plentiful annotations (e.g., POS tagging on Penn Treebank) is used to improve performance on a target task with fewer available annotations (e.g., POS tagging for microblogs). We examine the effects of transfer learning for deep hierarchical recurrent networks across domains, applications, and languages, and show that significant improvement can often be obtained. These improvements lead to improvements over the current state-of-the-art on several well-studied tasks.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1703.06345")
get_code_for_paper("1703.06345")
have("1703.06345")
Connect an agent — have() is free.