We lifted 1 functions out of this paper's own repositories and ran 0 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 |
|---|---|---|
| chunhuililili/mt_dnn | canonical | 0 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| create_model | Not yet run | chunhuililili/mt_dnn/hnn/src/apps/run_hnn.py code served (permissive licence) · get_code("7195b60542d1656f") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
This paper proposes a hybrid neural network (HNN) model for commonsense reasoning. An HNN consists of two component models, a masked language model and a semantic similarity model, which share a BERT-based contextual encoder but use different model-specific input and output layers. HNN obtains new state-of-the-art results on three classic commonsense reasoning tasks, pushing the WNLI benchmark to 89%, the Winograd Schema Challenge (WSC) benchmark to 75.1%, and the PDP60 benchmark to 90.0%. An ablation study shows that language models and semantic similarity models are complementary approaches to commonsense reasoning, and HNN effectively combines the strengths of both. The code and pre-trained models will be publicly available at https://github.com/namisan/mt-dnn.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1907.11983")
get_code_for_paper("1907.11983")
have("1907.11983")
Connect an agent — have() is free.