AugSumm: towards generalizable speech summarization using synthetic labels from large language model

• URL: http://arxiv.org/abs/2401.06806v1
• Date: Wed, 10 Jan 2024 18:39:46 GMT
• Title: AugSumm: towards generalizable speech summarization using synthetic labels from large language model
• Authors: Jee-weon Jung, Roshan Sharma, William Chen, Bhiksha Raj, Shinji Watanabe
• Abstract summary: Abstractive speech summarization (SSUM) aims to generate human-like summaries from speech. conventional SSUM models are mostly trained and evaluated with a single ground-truth (GT) human-annotated deterministic summary. We propose AugSumm, a method to leverage large language models (LLMs) as a proxy for human annotators to generate augmented summaries.
• Score: 61.73741195292997
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Abstractive speech summarization (SSUM) aims to generate human-like summaries from speech. Given variations in information captured and phrasing, recordings can be summarized in multiple ways. Therefore, it is more reasonable to consider a probabilistic distribution of all potential summaries rather than a single summary. However, conventional SSUM models are mostly trained and evaluated with a single ground-truth (GT) human-annotated deterministic summary for every recording. Generating multiple human references would be ideal to better represent the distribution statistically, but is impractical because annotation is expensive. We tackle this challenge by proposing AugSumm, a method to leverage large language models (LLMs) as a proxy for human annotators to generate augmented summaries for training and evaluation. First, we explore prompting strategies to generate synthetic summaries from ChatGPT. We validate the quality of synthetic summaries using multiple metrics including human evaluation, where we find that summaries generated using AugSumm are perceived as more valid to humans. Second, we develop methods to utilize synthetic summaries in training and evaluation. Experiments on How2 demonstrate that pre-training on synthetic summaries and fine-tuning on GT summaries improves ROUGE-L by 1 point on both GT and AugSumm-based test sets. AugSumm summaries are available at https://github.com/Jungjee/AugSumm.

Related papers

• Information-Theoretic Distillation for Reference-less Summarization [67.51150817011617]
  We present a novel framework to distill a powerful summarizer based on the information-theoretic objective for summarization. We start off from Pythia-2.8B as the teacher model, which is not yet capable of summarization. We arrive at a compact but powerful summarizer with only 568M parameters that performs competitively against ChatGPT.
  arXiv  Detail & Related papers  (2024-03-20T17:42:08Z)
• Source Identification in Abstractive Summarization [0.8883733362171033]
  We define input sentences that contain essential information in the generated summary as $textitsource sentences$ and study how abstractive summaries are made by analyzing the source sentences. We formulate automatic source sentence detection and compare multiple methods to establish a strong baseline for the task. Experimental results show that the perplexity-based method performs well in highly abstractive settings, while similarity-based methods robustly in relatively extractive settings.
  arXiv  Detail & Related papers  (2024-02-07T09:09:09Z)
• On Context Utilization in Summarization with Large Language Models [83.84459732796302]
  Large language models (LLMs) excel in abstractive summarization tasks, delivering fluent and pertinent summaries. Recent advancements have extended their capabilities to handle long-input contexts, exceeding 100k tokens. We conduct the first comprehensive study on context utilization and position bias in summarization.
  arXiv  Detail & Related papers  (2023-10-16T16:45:12Z)
• How Ready are Pre-trained Abstractive Models and LLMs for Legal Case Judgement Summarization? [4.721618284417204]
  In recent years, abstractive summarization models are gaining popularity. Legal domain-specific pre-trained abstractive summarization models are now available. General-domain pre-trained Large Language Models (LLMs) are known to generate high-quality text.
  arXiv  Detail & Related papers  (2023-06-02T03:16:19Z)
• Lay Text Summarisation Using Natural Language Processing: A Narrative Literature Review [1.8899300124593648]
  The aim of this literature review is to describe and compare the different text summarisation approaches used to generate lay summaries. We screened 82 articles and included eight relevant papers published between 2020 and 2021, using the same dataset. A combination of extractive and abstractive summarisation methods in a hybrid approach was found to be most effective.
  arXiv  Detail & Related papers  (2023-03-24T18:30:50Z)
• Generating Multiple-Length Summaries via Reinforcement Learning for Unsupervised Sentence Summarization [44.835811239393244]
  Sentence summarization shortens given texts while maintaining core contents of the texts. Unsupervised approaches have been studied to summarize texts without human-written summaries. We devise an abstractive model based on reinforcement learning without ground-truth summaries.
  arXiv  Detail & Related papers  (2022-12-21T08:34:28Z)
• MACSum: Controllable Summarization with Mixed Attributes [56.685735509260276]
  MACSum is the first human-annotated summarization dataset for controlling mixed attributes. We propose two simple and effective parameter-efficient approaches for the new task of mixed controllable summarization.
  arXiv  Detail & Related papers  (2022-11-09T17:17:37Z)
• Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees [89.60269205320431]
  Current abstractive summarization models either suffer from a lack of clear interpretability or provide incomplete rationales. We propose the Summarization Program (SP), an interpretable modular framework consisting of an (ordered) list of binary trees. A Summarization Program contains one root node per summary sentence, and a distinct tree connects each summary sentence to the document sentences.
  arXiv  Detail & Related papers  (2022-09-21T16:50:22Z)
• ARMAN: Pre-training with Semantically Selecting and Reordering of Sentences for Persian Abstractive Summarization [7.16879432974126]
  We propose ARMAN, a Transformer-based encoder-decoder model pre-trained with three novel objectives to address this issue. In ARMAN, salient sentences from a document are selected according to a modified semantic score to be masked and form a pseudo summary. We show that our proposed model achieves state-of-the-art performance on all six summarization tasks measured by ROUGE and BERTScore.
  arXiv  Detail & Related papers  (2021-09-09T08:35:39Z)
• Controllable Abstractive Dialogue Summarization with Sketch Supervision [56.59357883827276]
  Our model achieves state-of-the-art performance on the largest dialogue summarization corpus SAMSum, with as high as 50.79 in ROUGE-L score.
  arXiv  Detail & Related papers  (2021-05-28T19:05:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.