Ife Adebara will present a research seminar titled ‘Translating the Unseen? Yorùbá→English MT in Low-Resource, Morphologically-Unmarked Settings’
Click to join Zoom meeting. The passcode is 635410. (The meeting ID is 647 6334 5823.)
Translating the Unseen? Yorùbá→English MT in Low-Resource, Morphologically-Unmarked Settings
Translating between languages where certain features are marked morphologically in one but absent or marked contextually in the other is an important discourse phenomena for machine translation. When trans- lating from English which marks (in)definiteness morphologically, into Yorùbá which uses bare nouns but marks these features contextually, certain ambiguities arise. In this work, we perform fine-grained analysis on how an SMT system compares with two NMT systems (BiLSTM and Transformer) when translating bare nouns in Yorùbá into English. We investigate to what extent they identify BNs, correctly translate them and compare with human translation patterns. We also analyze the type of errors each model makes and provide a linguistic description of these errors. We glean insights for evaluating model performance in low resource settings. In translating bare nouns, our results show the transformer model outperfom the SMT and BILSTM model for one category while the SMT outperforms the NMT models for other categories.
