Dzmitry Bahdanau

Belarusian computer scientist and first author of 'Neural Machine Translation by Jointly Learning to Align and Translate' (2014; ICLR 2015), the paper that introduced the modern attentionattention, n.: A way for an AI model to choose what to focus on. For each word it processes, the model scores how relevant every other word is and draws information mostly from the relevant ones. mechanism for language. Working as a visiting student with Yoshua BengioYoshua Bengio, prop. n.: A Canadian computer scientist who helped found deep learning, including ideas behind today's language models, and who has become a leading voice on the risks of advanced AI. and Kyunghyun ChoKyunghyun Cho, prop. n.: A South Korean computer scientist who co-invented the encoder–decoder approach to neural machine translation and the gated recurrent unit, and co-wrote the paper that introduced attention. in Montreal, he let a recurrentrecurrent neural network, n.: A neural network that reads a sequence, such as a sentence or an audio clip, one piece at a time, carrying a running summary forward so that what came earlier can shape how later pieces are understood. decoder compute, at each output word, a learned soft weighting over all encoder states, so that the model learns which source words to align with; this removed the bottleneck of compressing a whole sentence into one fixed-length vector. The approach rapidly became standard in machine translationmachine translation, n.: Software that renders writing or speech in one language into another language, as online translation services and phone translation apps do. and sequence-to-sequencesequence-to-sequence model, n.: A model that turns one sequence into another, such as a French sentence into English or speech into text, by first reading the whole input and then writing the output step by step. models, and the transformertransformer, n.: The design behind today's chatbots and much of modern AI. It handles text by letting every word look at every other word and decide which of them matter for understanding it. (2017) built an entire architecture from attention. He completed a PhD at the Université de Montréal and later worked at Element AI and ServiceNow Research and as an adjunct professor at McGill University, on language agents, code models and systematic generalization.