Article

A fair, reproducible benchmark of EEG, speech, and interview text for depression detection, showing that fusing all three signals works best.

memBERT gives a transformer a memory of plain-text expert explanations, so each prediction points to the rationale behind it while keeping classification performance.

TC-GNN constrains graph pooling to pick out tree-kernel fragments of a sentence parse, and uses them to detect claims and premises across four corpora.