Unsupervised Dialogue Topic Segmentation in Hyperdimensional Space

TL;DR

HyperSeg introduces a hyperdimensional computing method for unsupervised dialogue topic segmentation, outperforming existing methods in accuracy and speed, and enhancing downstream summarization tasks.

Contribution

The paper presents HyperSeg, a novel HDC-based approach that significantly improves unsupervised dialogue topic segmentation performance and efficiency.

Findings

Outperforms 4 out of 5 segmentation benchmarks

Is 10 times faster than baseline methods

Enhances downstream summarization accuracy

Abstract

We present HyperSeg, a hyperdimensional computing (HDC) approach to unsupervised dialogue topic segmentation. HDC is a class of vector symbolic architectures that leverages the probabilistic orthogonality of randomly drawn vectors at extremely high dimensions (typically over 10,000). HDC generates rich token representations through its low-cost initialization of many unrelated vectors. This is especially beneficial in topic segmentation, which often operates as a resource-constrained pre-processing step for downstream transcript understanding tasks. HyperSeg outperforms the current state-of-the-art in 4 out of 5 segmentation benchmarks -- even when baselines are given partial access to the ground truth -- and is 10 times faster on average. We show that HyperSeg also improves downstream summarization accuracy. With HyperSeg, we demonstrate the viability of HDC in a major language task. We open-source HyperSeg to provide a strong baseline for unsupervised topic segmentation.