English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We present minicons, an open source library that provides a standard API forresearchers interested in conducting behavioral and representational analysesof transformer-based language models (LMs). Specifically, minicons enablesresearchers to apply analysis methods at two levels: (1) at the predictionlevel -- by providing functions to efficiently extract word/sentence levelprobabilities; and (2) at the representational level -- by also facilitatingefficient extraction of word/phrase level vectors from one or more layers. Inthis paper, we describe the library and apply it to two motivating casestudies: One focusing on the learning dynamics of the BERT architecture onrelative grammatical judgments, and the other on benchmarking 23 different LMson zero-shot abductive reasoning. minicons is available athttps://github.com/kanishkamisra/minicons

minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Models