Reproduce “Counseling Summarization using Mental Health Knowledge Guided Utterance Filtering” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Aseem Srivastava, Tharun Suresh, Sarah Peregrine, Lord, Md. Shad Akhtar, Tanmoy Chakraborty
ConSum summarizes psychotherapy conversations by combining a PHQ-9-based symptom filter and classifiers for counseling components and discussion filler, then sending selected, labeled utterances to T5. On MEMO’s 212-dialogue test set, it scores 45.36 ROUGE-1 versus 34.24 for the best baseline on that metric, but does not lead on ROUGE-L or QuestEval; the method remains tailored to counseling and depressive symptoms.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.