We lifted 5 functions out of this paper's own repositories and ran 2 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 |
|---|---|---|
| uchange/ulangel | reimplementation | 2 of 2 |
| prajjwal1/language-modelling | reimplementation | 0 of 3 |
| Function | Status | Where it lives |
|---|---|---|
| lower_tw | Ran | uchange/ulangel/ulangel/data/text_processor.py code served (permissive licence) · get_code("80418ee432e95278") |
| toLowercase | Ran | uchange/ulangel/ulangel/data/text_processor.py code served (permissive licence) · get_code("6ee9ad2657174087") |
| get_texts | Not yet run | prajjwal1/language-modelling/ULMfit.py pointer only (licence: NONE) · get_code("2a2b16561a736d43") |
| repackage_var | Not yet run | prajjwal1/language-modelling/fastai/lm_rnn.py pointer only (licence: NONE) · get_code("e18c93c24e6c53bf") |
| seq2seq_reg | Not yet run | prajjwal1/language-modelling/fastai/lm_rnn.py pointer only (licence: NONE) · get_code("929d963d360617be") |
More are linked than shown here.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Inductive transfer learning has greatly impacted computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch. We propose Universal Language Model Fine-tuning (ULMFiT), an effective transfer learning method that can be applied to any task in NLP, and introduce techniques that are key for fine-tuning a language model. Our method significantly outperforms the state-of-the-art on six text classification tasks, reducing the error by 18-24% on the majority of datasets. Furthermore, with only 100 labeled examples, it matches the performance of training from scratch on 100x more data. We open-source our pretrained models and code.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1801.06146")
get_code_for_paper("1801.06146")
have("1801.06146")
Connect an agent — have() is free.