Journal
EXPERT SYSTEMS WITH APPLICATIONS
Volume 174, Issue -, Pages -Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.eswa.2021.114704
Keywords
Arithmetic word problems; Recursive neural networks; Information extraction; Natural language processing
Categories
Funding
- European Union [761488]
- Flemish Government under the Onderzoeksprogramma Artificiele Intelligentie (AI) Vlaanderen programme
Ask authors/readers for more resources
This study proposes a method for solving arithmetic word problems in natural language processing systems, using Tree-RNN to score candidate solution equations. Experimental results show that this method outperforms previous algorithms in terms of accuracy.
Solving arithmetic word problems is a cornerstone task in assessing language understanding and reasoning capabilities in NLP systems. Recent works use automatic extraction and ranking of candidate solution equations providing the answer to arithmetic word problems. In this work, we explore novel approaches to score such candidate solution equations using tree-structured recursive neural network (Tree-RNN) configurations. The advantage of this Tree-RNN approach over using more established sequential representations, is that it can naturally capture the structure of the equations. Our proposed method consists of transforming the mathematical expression of the equation into an expression tree. Further, we encode this tree into a Tree-RNN by using different Tree-LSTM architectures. Experimental results show that our proposed method (i) improves overall performance with more than 3% accuracy points compared to previous state-of-the-art, and with over 15% points on a subset of problems that require more complex reasoning, and (ii) outperforms sequential LSTMs by 4% accuracy points on such more complex problems.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available