We lifted 6 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 |
|---|---|---|
| doheejin/protact | canonical | 0 of 6 |
| Function | Status | Where it lives |
|---|---|---|
| correlation_coefficient | Not yet run | doheejin/protact/models/ProTACT.py code served (permissive licence) · get_code("b87a7b824e631afa") |
| cosine_sim | Not yet run | doheejin/protact/models/ProTACT.py code served (permissive licence) · get_code("32688baeee05d994") |
| kendall_tau | Not yet run | doheejin/protact/metrics/metrics.py code served (permissive licence) · get_code("281c6b1b924b4507") |
| masked_loss_function | Not yet run | doheejin/protact/models/CTS_baseline.py code served (permissive licence) · get_code("7afa82514bf62dd5") |
| spearman | Not yet run | doheejin/protact/metrics/metrics.py code served (permissive licence) · get_code("c6dcfcf2849e86cd") |
| trait_sim_loss | Not yet run | doheejin/protact/models/ProTACT.py code served (permissive licence) · get_code("bb31be7285eb8e10") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Automated essay scoring (AES) aims to score essays written for a given prompt, which defines the writing topic. Most existing AES systems assume to grade essays of the same prompt as used in training and assign only a holistic score. However, such settings conflict with real-education situations; pre-graded essays for a particular prompt are lacking, and detailed trait scores of sub-rubrics are required. Thus, predicting various trait scores of unseen-prompt essays (called cross-prompt essay trait scoring) is a remaining challenge of AES. In this paper, we propose a robust model: prompt- and trait relation-aware cross-prompt essay trait scorer. We encode prompt-aware essay representation by essay-prompt attention and utilizing the topic-coherence feature extracted by the topic-modeling mechanism without access to labeled data; therefore, our model considers the prompt adherence of an essay, even in a cross-prompt setting. To facilitate multi-trait scoring, we design trait-similarity loss that encapsulates the correlations of traits. Experiments prove the efficacy of our model, showing state-of-the-art results for all prompts and traits. Significant improvements in low-resource-prompt and inferior traits further indicate our model's strength.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2305.16826")
get_code_for_paper("2305.16826")
have("2305.16826")
Connect an agent — have() is free.