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

Answering questions asked from instructional corpora such as E-manuals,recipe books, etc., has been far less studied than open-domain factoidcontext-based question answering. This can be primarily attributed to theabsence of standard benchmark datasets. In this paper we meticulously create alarge amount of data connected with E-manuals and develop suitable algorithm toexploit it. We collect E-Manual Corpus, a huge corpus of 307,957 E-manuals andpretrain RoBERTa on this large corpus. We create various benchmark QA datasetswhich include question answer pairs curated by experts based upon twoE-manuals, real user questions from Community Question Answering Forumpertaining to E-manuals etc. We introduce EMQAP (E-Manual Question AnsweringPipeline) that answers questions pertaining to electronics devices. Built uponthe pretrained RoBERTa, it harbors a supervised multi-task learning frameworkwhich efficiently performs the dual tasks of identifying the section in theE-manual where the answer can be found and the exact answer span within thatsection. For E-Manual annotated question-answer pairs, we show an improvementof about 40% in ROUGE-L F1 scores over the most competitive baseline. Weperform a detailed ablation study and establish the versatility of EMQAP acrossdifferent circumstances. The code and datasets are shared athttps://github.com/abhi1nandy2/EMNLP-2021-Findings, and the correspondingproject website is https://sites.google.com/view/emanualqa/home.

Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework