From Local to Global: A Graph RAG Approach to Query-Focused Summarization

no code implementations • 24 Apr 2024 • Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Jonathan Larson

To combine the strengths of these contrasting methods, we propose a Graph RAG approach to question answering over private text corpora that scales with both the generality of user questions and the quantity of source text to be indexed.

Query-focused Summarization Question Answering +1

Discovering Communication Pattern Shifts in Large-Scale Labeled Networks using Encoder Embedding and Vertex Dynamics

1 code implementation • 3 May 2023 • Cencheng Shen, Jonathan Larson, Ha Trinh, Xihan Qin, Youngser Park, Carey E. Priebe

Analyzing large-scale time-series network data, such as social media and email communications, poses a significant challenge in understanding social dynamics, detecting anomalies, and predicting trends.

Time Series

Synergistic Graph Fusion via Encoder Embedding

1 code implementation • 31 Mar 2023 • Cencheng Shen, Carey E. Priebe, Jonathan Larson, Ha Trinh

In this paper, we introduce a novel approach called graph fusion embedding, designed for multi-graph embedding with shared vertex sets.

Classification Graph Embedding +1

Applying Prediction Techniques to Phoneme-based AAC Systems

no code implementations • WS 2012 • Ha Trinh, Annalu Waller, Keith Vertanen, Per Ola Kristensson, Vicki L. Hanson