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

Hybrid data combining both tabular and textual content (e.g., financialreports) are quite pervasive in the real world. However, Question Answering(QA) over such hybrid data is largely neglected in existing research. In thiswork, we extract samples from real financial reports to build a new large-scaleQA dataset containing both Tabular And Textual data, named TAT-QA, wherenumerical reasoning is usually required to infer the answer, such as addition,subtraction, multiplication, division, counting, comparison/sorting, and thecompositions. We further propose a novel QA model termed TAGOP, which iscapable of reasoning over both tables and text. It adopts sequence tagging toextract relevant cells from the table along with relevant spans from the textto infer their semantics, and then applies symbolic reasoning over them with aset of aggregation operators to arrive at the final answer. TAGOPachieves 58.0%inF1, which is an 11.1% absolute increase over the previous best baselinemodel, according to our experiments on TAT-QA. But this result still lags farbehind performance of expert human, i.e.90.8% in F1. It is demonstrated thatour TAT-QA is very challenging and can serve as a benchmark for training andtesting powerful QA models that address hybrid form data.

TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance