Papers › Interpretable Textual Neuron Representations for NLP

Interpretable Textual Neuron Representations for NLP

19 Sep 2018WS 2018 11arXiv:1809.07291archive 2025-07-28

Nina Poerner, Benjamin Roth, Hinrich Schütze

Input optimization methods, such as Google Deep Dream, create interpretable representations of neurons for computer vision DNNs. We propose and evaluate ways of transferring this technology to NLP. Our results suggest that gradient ascent with a gumbel softmax layer produces n-gram representations that outperform naive corpus search in terms of target neuron activation. The representations highlight differences in syntax awareness between the language and visual models of the Imaginet architecture.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

NPoe/input-optimization-nlp officialmentioned in paper report
phnk/D7047E mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Gumbel SoftmaxSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections