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

Math word problems form a natural abstraction to a range of quantitativereasoning problems, such as understanding financial news, sports results, andcasualties of war. Solving such problems requires the understanding of severalmathematical concepts such as dimensional analysis, subset relationships, etc.In this paper, we develop declarative rules which govern the translation ofnatural language description of these concepts to math expressions. We thenpresent a framework for incorporating such declarative knowledge into wordproblem solving. Our method learns to map arithmetic word problem text to mathexpressions, by learning to select the relevant declarative knowledge for eachoperation of the solution expression. This provides a way to handle multipleconcepts in the same problem while, at the same time, support interpretabilityof the answer expression. Our method models the mapping to declarativeknowledge as a latent variable, thus removing the need for expensiveannotations. Experimental evaluation suggests that our domain knowledge basedsolver outperforms all other systems, and that it generalizes better in therealistic case where the training data it is exposed to is biased in adifferent way than the test data.

Mapping to Declarative Knowledge for Word Problem Solving