COLO: A Contrastive Learning based Re-ranking Framework for One-Stage Summarization

• URL: http://arxiv.org/abs/2209.14569v2
• Date: Wed, 19 Apr 2023 07:01:18 GMT
• Title: COLO: A Contrastive Learning based Re-ranking Framework for One-Stage Summarization
• Authors: Chenxin An, Ming Zhong, Zhiyong Wu, Qin Zhu, Xuanjing Huang, Xipeng Qiu
• Abstract summary: We propose a Contrastive Learning based re-ranking framework for one-stage summarization called COLO. COLO boosts the extractive and abstractive results of one-stage systems on CNN/DailyMail benchmark to 44.58 and 46.33 ROUGE-1 score.
• Score: 84.70895015194188
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Traditional training paradigms for extractive and abstractive summarization systems always only use token-level or sentence-level training objectives. However, the output summary is always evaluated from summary-level which leads to the inconsistency in training and evaluation. In this paper, we propose a Contrastive Learning based re-ranking framework for one-stage summarization called COLO. By modeling a contrastive objective, we show that the summarization model is able to directly generate summaries according to the summary-level score without additional modules and parameters. Extensive experiments demonstrate that COLO boosts the extractive and abstractive results of one-stage systems on CNN/DailyMail benchmark to 44.58 and 46.33 ROUGE-1 score while preserving the parameter efficiency and inference efficiency. Compared with state-of-the-art multi-stage systems, we save more than 100 GPU training hours and obtaining 3~8 speed-up ratio during inference while maintaining comparable results.

Related papers

• Towards Enhancing Coherence in Extractive Summarization: Dataset and Experiments with LLMs [70.15262704746378]
  We propose a systematically created human-annotated dataset consisting of coherent summaries for five publicly available datasets and natural language user feedback. Preliminary experiments with Falcon-40B and Llama-2-13B show significant performance improvements (10% Rouge-L) in terms of producing coherent summaries.
  arXiv  Detail & Related papers  (2024-07-05T20:25:04Z)
• Unsupervised Video Summarization via Reinforcement Learning and a Trained Evaluator [5.530212768657544]
  This paper presents a novel approach for unsupervised video summarization using reinforcement learning. It aims to address the existing limitations of current unsupervised methods, including unstable training of adversarial generator-discriminator architectures. Experimental results demonstrate promising performance, with F-scores of 62.3 and 54.5 on TVSum and SumMe datasets, respectively.
  arXiv  Detail & Related papers  (2024-07-05T05:08:06Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Lexical Repetitions Lead to Rote Learning: Unveiling the Impact of Lexical Overlap in Train and Test Reference Summaries [131.80860903537172]
  Ideal summarization models should generalize to novel summary-worthy content without remembering reference training summaries by rote. We propose a fine-grained evaluation protocol by partitioning a test set based on the lexical similarity of reference test summaries with training summaries.
  arXiv  Detail & Related papers  (2023-11-15T23:47:53Z)
• PromptSum: Parameter-Efficient Controllable Abstractive Summarization [4.145362426026615]
  We introduce PromptSum, a method combining PT with a multi-task objective and discrete entity prompts for abstractive summarization. Our model competitive ROUGE results on popular abstractive summarization benchmarks coupled with a strong level of controllability through entities.
  arXiv  Detail & Related papers  (2023-08-06T13:54:14Z)
• Improving the Faithfulness of Abstractive Summarization via Entity Coverage Control [27.214742188672464]
  We propose a method to remedy entity-level hallucinations with Entity Coverage Control (ECC) ECC computes entity coverage precision and prepend the corresponding control code for each training example. We show that the proposed method leads to more faithful and salient abstractive summarization in supervised fine-tuning and zero-shot settings.
  arXiv  Detail & Related papers  (2022-07-05T18:52:19Z)
• Dense Unsupervised Learning for Video Segmentation [49.46930315961636]
  We present a novel approach to unsupervised learning for video object segmentation (VOS) Unlike previous work, our formulation allows to learn dense feature representations directly in a fully convolutional regime. Our approach exceeds the segmentation accuracy of previous work despite using significantly less training data and compute power.
  arXiv  Detail & Related papers  (2021-11-11T15:15:11Z)
• SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization [14.16710715347118]
  We present a conceptually simple while empirically powerful framework for abstractive summarization Sim. With minor modification over existing top-scoring systems, Sim can improve the performance of existing top-performing systems by a large margin. Results of our proposed models have been deployed into ExplainaBoard platform, which allows researchers to understand our systems in a more fine-grained way.
  arXiv  Detail & Related papers  (2021-06-03T14:34:17Z)
• The Summary Loop: Learning to Write Abstractive Summaries Without Examples [21.85348918324668]
  This work presents a new approach to unsupervised abstractive summarization based on maximizing a combination of coverage and fluency for a given length constraint. Key terms are masked out of the original document and must be filled in by a coverage model using the current generated summary. When tested on popular news summarization datasets, the method outperforms previous unsupervised methods by more than 2 R-1 points.
  arXiv  Detail & Related papers  (2021-05-11T23:19:46Z)
• Pre-training for Abstractive Document Summarization by Reinstating Source Text [105.77348528847337]
  This paper presents three pre-training objectives which allow us to pre-train a Seq2Seq based abstractive summarization model on unlabeled text. Experiments on two benchmark summarization datasets show that all three objectives can improve performance upon baselines.
  arXiv  Detail & Related papers  (2020-04-04T05:06:26Z)

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.