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

Question answering requiring discrete reasoning, e.g., arithmetic computing,comparison, and counting, over knowledge is a challenging task. In this paper,we propose UniRPG, a semantic-parsing-based approach advanced ininterpretability and scalability, to perform unified discrete reasoning overheterogeneous knowledge resources, i.e., table and text, as program generation.Concretely, UniRPG consists of a neural programmer and a symbolic programexecutor, where a program is the composition of a set of pre-defined generalatomic and higher-order operations and arguments extracted from table and text.First, the programmer parses a question into a program by generating operationsand copying arguments, and then the executor derives answers from table andtext based on the program. To alleviate the costly program annotation issue, wedesign a distant supervision approach for programmer learning, where pseudoprograms are automatically constructed without annotated derivations. Extensiveexperiments on the TAT-QA dataset show that UniRPG achieves tremendousimprovements and enhances interpretability and scalability compared withstate-of-the-art methods, even without derivation annotation. Moreover, itachieves promising performance on the textual dataset DROP without derivations.

UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation