Which of the following contributors to the Transformer model is best known for introducing the concept of self-attention, which allows the model to weigh the importance of different words in a sentence?

The concept of self‑attention was introduced by Ashish Vaswani, one of the authors of the original Transformer paper. He showed that a model could compute a weighted sum of all words in a sentence, letting each word decide how much it should pay attention to every other word. This idea lets the model focus on the most relevant words regardless of their position. For example, in the sentence “The cat sat on the mat,” the word “cat” can give more weight to “sat” than to “on” when predicting the next word. Vaswani’s self‑attention mechanism became the core of modern language models.