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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Natural language explanation (NLE) models aim at explaining thedecision-making process of a black box system via generating natural languagesentences which are human-friendly, high-level and fine-grained. Current NLEmodels explain the decision-making process of a vision or vision-language model(a.k.a., task model), e.g., a VQA model, via a language model (a.k.a.,explanation model), e.g., GPT. Other than the additional memory resources andinference time required by the task model, the task and explanation models arecompletely independent, which disassociates the explanation from the reasoningprocess made to predict the answer. We introduce NLX-GPT, a general, compactand faithful language model that can simultaneously predict an answer andexplain it. We first conduct pre-training on large scale data of image-captionpairs for general understanding of images, and then formulate the answer as atext prediction task along with the explanation. Without region proposals nor atask model, our resulting overall framework attains better evaluation scores,contains much less parameters and is 15$\times$ faster than the current SoAmodel. We then address the problem of evaluating the explanations which can bein many times generic, data-biased and can come in several forms. We thereforedesign 2 new evaluation measures: (1) explain-predict and (2) retrieval-basedattack, a self-evaluation framework that requires no labels. Code is at:https://github.com/fawazsammani/nlxgpt.

NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks