6 citations · 15 across the 7 of their papers we have counts for
7 papers
Unsupervised Extractive Dialogue Summarization in Hyperdimensional Space
Seongmin Park, Kyungho Kim, Jaejin Seo +1
We present HyperSum, an extractive summarization framework that captures both the efficiency of traditional lexical summarization and the accuracy of contemporary neural approaches…
Unsupervised Dialogue Topic Segmentation in Hyperdimensional Space
Seongmin Park, Jinkyu Seo, Jihwa Lee
We present HyperSeg, a hyperdimensional computing (HDC) approach to unsupervised dialogue topic segmentation. HDC is a class of vector symbolic architectures that leverages the pro…
Leveraging Non-dialogue Summaries for Dialogue Summarization
Seongmin Park, Dongchan Shin, Jihwa Lee
To mitigate the lack of diverse dialogue summarization datasets in academia, we present methods to utilize non-dialogue summarization data for enhancing dialogue summarization syst…
LIME: Weakly-Supervised Text Classification Without Seeds
Seongmin Park, Jihwa Lee
In weakly-supervised text classification, only label names act as sources of supervision. Predominant approaches to weakly-supervised text classification utilize a two-phase framew…
Unsupervised Abstractive Dialogue Summarization with Word Graphs and POV Conversion
Seongmin Park, Jihwa Lee
We advance the state-of-the-art in unsupervised abstractive dialogue summarization by utilizing multi-sentence compression graphs. Starting from well-founded assumptions about word…
Improving Distinction between ASR Errors and Speech Disfluencies with Feature Space Interpolation
Seongmin Park, Dongchan Shin, Sangyoun Paik +3
Fine-tuning pretrained language models (LMs) is a popular approach to automatic speech recognition (ASR) error detection during post-processing. While error detection systems often…
Finetuning Pretrained Transformers into Variational Autoencoders
Seongmin Park, Jihwa Lee
Text variational autoencoders (VAEs) are notorious for posterior collapse, a phenomenon where the model's decoder learns to ignore signals from the encoder. Because posterior colla…