SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.11034 · 2022

Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 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.

RepositoryRoleRan
hyunsoocho77/lacl-official canonical 8 of 9
FunctionStatusWhere it lives
Supervised_NT_xent Ran hyunsoocho77/lacl-official/loss.py
code served (permissive licence) · get_code("8009738e5585203d")
collate_fn Ran hyunsoocho77/lacl-official/utils.py
code served (permissive licence) · get_code("24b2927037c0889f")
collate_fn2 Ran hyunsoocho77/lacl-official/utils.py
code served (permissive licence) · get_code("e5c1aadbdcf0a0eb")
fpr_at_95 Ran hyunsoocho77/lacl-official/evaluation.py
code served (permissive licence) · get_code("1388ea7bf1dcf255")
get_sim_mat Ran hyunsoocho77/lacl-official/loss.py
code served (permissive licence) · get_code("3aa2f062aac00de2")
mean_pooling Ran hyunsoocho77/lacl-official/model.py
code served (permissive licence) · get_code("7e7ca6d67f5c378d")
merge_keys Ran hyunsoocho77/lacl-official/evaluation.py
code served (permissive licence) · get_code("779bf38fd1a03f1f")
reg_loss Ran hyunsoocho77/lacl-official/loss.py
code served (permissive licence) · get_code("bdbebc60e2bde280")
LACL_load_aug Not yet run hyunsoocho77/lacl-official/utils.py
code served (permissive licence) · get_code("5cb7b677118e1dba")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Out-of-distribution (OOD) detection aims to discern outliers from the intended data distribution, which is crucial to maintaining high reliability and a good user experience. Most recent studies in OOD detection utilize the information from a single representation that resides in the penultimate layer to determine whether the input is anomalous or not. Although such a method is straightforward, the potential of diverse information in the intermediate layers is overlooked. In this paper, we propose a novel framework based on contrastive learning that encourages intermediate features to learn layer-specialized representations and assembles them implicitly into a single representation to absorb rich information in the pre-trained language model. Extensive experiments in various intent classification and OOD datasets demonstrate that our approach is significantly more effective than other works.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2210.11034")
get_code_for_paper("2210.11034")
have("2210.11034")

Connect an agent — have() is free.