Salience Allocation as Guidance for Abstractive Summarization
- URL: http://arxiv.org/abs/2210.12330v1
- Date: Sat, 22 Oct 2022 02:13:44 GMT
- Title: Salience Allocation as Guidance for Abstractive Summarization
- Authors: Fei Wang, Kaiqiang Song, Hongming Zhang, Lifeng Jin, Sangwoo Cho,
Wenlin Yao, Xiaoyang Wang, Muhao Chen, Dong Yu
- Abstract summary: We propose a novel summarization approach with a flexible and reliable salience guidance, namely SEASON (SaliencE Allocation as Guidance for Abstractive SummarizatiON)
SEASON utilizes the allocation of salience expectation to guide abstractive summarization and adapts well to articles in different abstractiveness.
- Score: 61.31826412150143
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Abstractive summarization models typically learn to capture the salient
information from scratch implicitly. Recent literature adds extractive
summaries as guidance for abstractive summarization models to provide hints of
salient content and achieves better performance. However, extractive summaries
as guidance could be over strict, leading to information loss or noisy signals.
Furthermore, it cannot easily adapt to documents with various abstractiveness.
As the number and allocation of salience content pieces vary, it is hard to
find a fixed threshold deciding which content should be included in the
guidance. In this paper, we propose a novel summarization approach with a
flexible and reliable salience guidance, namely SEASON (SaliencE Allocation as
Guidance for Abstractive SummarizatiON). SEASON utilizes the allocation of
salience expectation to guide abstractive summarization and adapts well to
articles in different abstractiveness. Automatic and human evaluations on two
benchmark datasets show that the proposed method is effective and reliable.
Empirical results on more than one million news articles demonstrate a natural
fifteen-fifty salience split for news article sentences, providing a useful
insight for composing news articles.
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) - OpineSum: Entailment-based self-training for abstractive opinion
summarization [6.584115526134759]
We present a novel self-training approach, OpineSum, for abstractive opinion summarization.
The summaries in this approach are built using a novel application of textual entailment.
OpineSum achieves state-of-the-art performance in both settings.
arXiv Detail & Related papers (2022-12-21T06:20:28Z) - A Survey on Neural Abstractive Summarization Methods and Factual
Consistency of Summarization [18.763290930749235]
summarization is the process of shortening a set of textual data computationally, to create a subset (a summary)
Existing summarization methods can be roughly divided into two types: extractive and abstractive.
An extractive summarizer explicitly selects text snippets from the source document, while an abstractive summarizer generates novel text snippets to convey the most salient concepts prevalent in the source.
arXiv Detail & Related papers (2022-04-20T14:56:36Z) - Subjective Bias in Abstractive Summarization [11.675414451656568]
We formulate the differences among possible multiple expressions summarizing the same content as subjective bias and examine the role of this bias in the context of abstractive summarization.
Results of summarization models trained on style-clustered datasets show that there are certain types of styles that lead to better convergence, abstraction and generalization.
arXiv Detail & Related papers (2021-06-18T12:17:55Z) - EASE: Extractive-Abstractive Summarization with Explanations [18.046254486733186]
We present an explainable summarization system based on the Information Bottleneck principle.
Inspired by previous research that humans use a two-stage framework to summarize long documents, our framework first extracts a pre-defined amount of evidence spans as explanations.
We show that explanations from our framework are more relevant than simple baselines, without substantially sacrificing the quality of the generated summary.
arXiv Detail & Related papers (2021-05-14T17:45:06Z) - Constrained Abstractive Summarization: Preserving Factual Consistency
with Constrained Generation [93.87095877617968]
We propose Constrained Abstractive Summarization (CAS), a general setup that preserves the factual consistency of abstractive summarization.
We adopt lexically constrained decoding, a technique generally applicable to autoregressive generative models, to fulfill CAS.
We observe up to 13.8 ROUGE-2 gains when only one manual constraint is used in interactive summarization.
arXiv Detail & Related papers (2020-10-24T00:27:44Z) - Better Highlighting: Creating Sub-Sentence Summary Highlights [40.46639471959677]
We present a new method to produce self-contained highlights that are understandable on their own to avoid confusion.
Our method combines determinantal point processes and deep contextualized representations to identify an optimal set of sub-sentence segments.
To demonstrate the flexibility and modeling power of our method, we conduct extensive experiments on summarization datasets.
arXiv Detail & Related papers (2020-10-20T18:57:42Z) - GSum: A General Framework for Guided Neural Abstractive Summarization [102.29593069542976]
We propose a general and guided summarization framework (GSum) that can effectively take different kinds of external guidance as input.
Experiments demonstrate that this model is effective, achieving state-of-the-art performance according to ROUGE on 4 popular summarization datasets.
arXiv Detail & Related papers (2020-10-15T20:46:14Z) - Few-Shot Learning for Opinion Summarization [117.70510762845338]
Opinion summarization is the automatic creation of text reflecting subjective information expressed in multiple documents.
In this work, we show that even a handful of summaries is sufficient to bootstrap generation of the summary text.
Our approach substantially outperforms previous extractive and abstractive methods in automatic and human evaluation.
arXiv Detail & Related papers (2020-04-30T15:37:38Z) - Unsupervised Opinion Summarization with Noising and Denoising [85.49169453434554]
We create a synthetic dataset from a corpus of user reviews by sampling a review, pretending it is a summary, and generating noisy versions thereof.
At test time, the model accepts genuine reviews and generates a summary containing salient opinions, treating those that do not reach consensus as noise.
arXiv Detail & Related papers (2020-04-21T16:54:57Z)
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.