2019/10/12 by Katharina Kann, Kann, Katharina · 6 citations
Computer Science · #Agglutinative language #Artificial intelligence #Artificial neural network #Computation and Language (cs.CL) #Computer science #FOS: Computer and information sciences #Inflection #Language acquisition #Linguistics #Morphology (biology) #Natural Language Processing Techniques #Natural language processing #Sequence (biology) #Speech and dialogue systems #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.1910.05456
published in arXiv (Cornell University) (Cornell University) · SCiL 2020
arxiv created 2019/10/12 · openalex publication_date 2019/10/12 · arxiv updated 2019/10/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
How does knowledge of one language's morphology influence learning of inflection rules in a second one? In order to investigate this question in artificial neural network models, we perform experiments with a sequence-to-sequence architecture, which we train on different combinations of eight source and three target languages. A detailed analysis of the model outputs suggests the following conclusions: (i) if source and target language are closely related, acquisition of the target language's inflectional morphology constitutes an easier task for the model; (ii) knowledge of a prefixing (resp. suffixing) language makes acquisition of a suffixing (resp. prefixing) language's morphology more challenging; and (iii) surprisingly, a source language which exhibits an agglutinative morphology simplifies learning of a second language's inflectional morphology, independent of their relatedness.