This work addresses the problem of encoding the video generated by the screen of an airplane cockpit. As other computer screens, cockpit screens consists in computer-generated graphics often atop natural background. Existing screen content coding schemes fail notably in preserving the readability of textual information at the low bitrates required in avionic applications. We propose a screen coding scheme where textual information is encoded according to the relative semantics rather than in the pixel domain. The encoder localizes textual information, the semantics of each character are extracted with a convolutional neural network and are predictively encoded. Text is then removed via inpainting, the residual background video is compressed with a standard codec and transmitted to the receiver together with the text semantics. At the decoder side, text is synthesized using the decoded semantics and superimposed over the decoded residual video recovering the original frame. Our proposed scheme offers two key advantages over a semantics-unaware scheme that encodes text in the pixel domain. First, the text readability at the decoder is not compromised by compression artifacts, whereas the relative bitrate is negligible. Second, removal of high-frequency transform coefficients associated to the inpainted text drastically reduces the bitrate of the residual video. Experiments with real cockpit video sequences show BD-rate gains up to 82% and 69 % over a reference H.265/HEVC encoder and its SCC extension. Moreover, our scheme achieves quasi-errorless character recognition already at very low bitrates, whereas even HEVC-SCC needs at least 3 or 4 times more bit-rate to achieve a comparable error rate.