Wei Wu, Xueliang Zhao, Chongyang Tao, Can Xu, Dongyan Zhao, Rui Yan
We lifted 6 functions out of this paper's own repositories and ran 5 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 |
|---|---|---|
| zhaoxlpku/KnowledGPT | — | 5 of 6 |
| Function | Status | Where it lives |
|---|---|---|
| LSTMPointerNet | Ran | zhaoxlpku/KnowledGPT/model/extract.py pointer only (licence: NONE) · get_code("2c3d3b3aca8701d4") |
| MultiLayerLSTMCells | Ran | zhaoxlpku/KnowledGPT/model/extract.py pointer only (licence: NONE) · get_code("f78a8f4acadeeb1c") |
| StackedLSTMCells | Ran | zhaoxlpku/KnowledGPT/model/extract.py pointer only (licence: NONE) · get_code("7cac2871a3399a82") |
| len_mask | Ran | zhaoxlpku/KnowledGPT/model/extract.py pointer only (licence: NONE) · get_code("56efb09918a6de86") |
| prob_normalize | Ran | zhaoxlpku/KnowledGPT/model/extract.py pointer only (licence: NONE) · get_code("98c4e5bfb69b2999") |
| PtrExtractSumm | Not yet run | zhaoxlpku/KnowledGPT/model/extract.py pointer only (licence: NONE) · get_code("df4ddb65b2d0aa48") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We study knowledge-grounded dialogue generation with pre-trained language models. To leverage the redundant external knowledge under capacity constraint, we propose equipping response generation defined by a pretrained language model with a knowledge selection module, and an unsupervised approach to jointly optimizing knowledge selection and response generation with unlabeled dialogues. Empirical results on two benchmarks indicate that our model can significantly outperform state-of-the-art methods in both automatic evaluation and human judgment.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2010.08824")
get_code_for_paper("2010.08824")
have("2010.08824")
Connect an agent — have() is free.