For learner $i$ at time step $t$, we denote the combination of the question that they answered, the concept this question covers, and their graded response as a tuple $(q_t^i, c_t^i, r_t^i)$, where $q_t^i \in \mathbb{N}^+$ is the question index, $c_t^i \in \mathbb{N}^+$ is the concept index, and $r_t^i \in \{0, 1\}$ is the response. Given a learner's past history up to time $t - 1$ as {(q_1, c_1, r_1), dots, (q_{t-1}, c_{t-1}, r_{t-1})}, the goal is to predict their response $r_t$ to question $q_t$ on concept $c_t$ at the current time step, $t$. Real-valued embedding vectors $x_t \in \mathbb{R}^D$ and $y_t \in \mathbb{R}^D$ are used to represent each question and each question-response pair $(q_t, r_t)$, respectively. $x_t$ characterizes information about questions, and $y_t$ characterizes the knowledge learners acquire by responding to questions, with two separate embeddings for correct and incorrect responses.