Liyanage VRanathunga S2025-08-062025-08-062020-01-01Liyanage V, Ranathunga S. (2020). Multi-lingual mathematical word problem generation using long short term memory networks with enhanced input features. Lrec 2020 12th International Conference on Language Resources and Evaluation Conference Proceedings. (pp. 4709-4716). European Language Resources Association (ELRA).https://mro.massey.ac.nz/handle/10179/73301A Mathematical Word Problem (MWP) differs from a general textual representation due to the fact that it is comprised of numerical quantities and units, in addition to text. Therefore, MWP generation should be carefully handled. When it comes to multi-lingual MWP generation, language specific morphological and syntactic features become additional constraints. Standard template-based MWP generation techniques are incapable of identifying these language specific constraints, particularly in morphologically rich yet low resource languages such as Sinhala and Tamil. This paper presents the use of a Long Short Term Memory (LSTM) network that is capable of generating elementary level MWPs, while satisfying the aforementioned constraints. Our approach feeds a combination of character embeddings, word embeddings, and Part of Speech (POS) tag embeddings to the LSTM, in which attention is provided for numerical values and units. We trained our model for three languages, English, Sinhala and Tamil using separate MWP datasets. Irrespective of the language and the type of the MWP, our model could generate accurate single sentenced and multi sentenced problems. Accuracy reported in terms of average BLEU score for English, Sinhala and Tamil languages were 22.97%, 24.49% and 20.74%, respectively.(c) The author/shttps://creativecommons.org/licenses/by-nc/4.0/deed.enEmbeddingsLanguage GenerationLow- resource LanguagesLSTMMathematical Word ProblemconferenceCC BY-NCc-conference-paper-in-proceedings4709-4716