Pith. sign in

Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Abstractive conversation summarization has received much attention recently. However, these generated summaries often suffer from insufficient, redundant, or incorrect content, largely due to the unstructured and complex characteristics of human-human interactions. To this end, we propose to explicitly model the rich structures in conversations for more precise and accurate conversation summarization, by first incorporating discourse relations between utterances and action triples ("who-doing-what") in utterances through structured graphs to better encode conversations, and then designing a multi-granularity decoder to generate summaries by combining all levels of information. Experiments show that our proposed models outperform state-of-the-art methods and generalize well in other domains in terms of both automatic evaluations and human judgments. We have publicly released our code at https://github.com/GT-SALT/Structure-Aware-BART.

fields

cs.CV 1

years

2025 1

verdicts

REJECT 1

representative citing papers

citing papers explorer

Showing 1 of 1 citing paper.

  • PresentAgent: Multimodal Agent for Presentation Video Generation cs.CV · 2025-07-05 · reject · none · ref 5 · internal anchor

    PresentAgent chains LLM segmentation, slide rendering, TTS, and ffmpeg to turn documents into narrated presentation videos, but the human-level claim rests on five documents and an unvalidated VLM judge.