Solving Probability Problems in Natural Language

By Anton Dries, Angelika Kimmig, Jesse Davis, Vaishak Belle, Luc De Raedt. 2017

22 citations recorded by the source corpus.

The ability to solve probability word problems such as those found in introductory discrete mathematics textbooks, is an important cognitive and intellectual skill. In this paper, we develop a two-step endto-end fully automated approach for solving such questions that is able to automatically provide answers to exercises about probability formulated in natural language. In the first step, a question formulated in natural language is analysed and transformed into a highlevel model specified in a declarative language. In the second step, a solution to the high-level model is computed using a probabilistic programming system. On a dataset of 2160 probability problems, our solver is able to correctly answer 97.5% of the questions given a correct model. On the end-toend evaluation, we are able to answer 12.5% of the questions (or 31.1% if we exclude examples not supported by design).

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Wei Dang Lu
2. Lei Wang
3. Bing Tian Dai
4. Dongxiang Zhang
5. Yanyan Zou
6. Heng Tao Shen
7. Vaishak Belle
8. Nuo Xu

Citations in the corpus

• Logic meets Probability: Towards Explainable AI Systems for Uncertain Worlds (2017, methodology): “The automated solving of such problems using probabilistic programming is considered in our recent work [Dries et al. , 2017].”
• Text2Math: End-to-end Parsing Text into Math Expressions (2019, background): “Other types of problems have also been investigated, including probability problems (Dries et al., 2017), logic puzzle problems (Mitra and Baral, 2015; Chesani et al., 2017) and geometry problems (Seo et al., 2014, 2015).”
• The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers (2018, methodology): “For other forms of math problems, [102] solves probability problems automatically by a two-step approach, namely first formulating questions in a declarative language and then computing the answer through a solver implemented in ProbLog [103].”