SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1902.07249 · 2019

Discovery of Natural Language Concepts in Individual Units of CNNs

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 1 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
seilna/CNN-Units-in-NLP canonical 1 of 3
FunctionStatusWhere it lives
sample_top Ran seilna/CNN-Units-in-NLP/code/utils.py
code served (permissive licence) · get_code("889fdbb32959107f")
html_per_tas Not yet run seilna/CNN-Units-in-NLP/code/utils.py
code served (permissive licence) · get_code("8198392778043324")
html_per_unit Not yet run seilna/CNN-Units-in-NLP/code/utils.py
code served (permissive licence) · get_code("31e27ca4e46dca13")

Repositories linked to this paper

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

Abstract

Although deep convolutional networks have achieved improved performance in many natural language tasks, they have been treated as black boxes because they are difficult to interpret. Especially, little is known about how they represent language in their intermediate layers. In an attempt to understand the representations of deep convolutional networks trained on language tasks, we show that individual units are selectively responsive to specific morphemes, words, and phrases, rather than responding to arbitrary and uninterpretable patterns. In order to quantitatively analyze such an intriguing phenomenon, we propose a concept alignment method based on how units respond to the replicated text. We conduct analyses with different architectures on multiple datasets for classification and translation tasks and provide new insights into how deep models understand natural language.

For agents

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

get_harvested_code_for_paper("1902.07249")
get_code_for_paper("1902.07249")
have("1902.07249")

Connect an agent — have() is free.