Related papers: BRIO: Bringing Order to Abstractive Summarization
Abstractive text summarization is integral to the Big Data era, which demands advanced methods to turn voluminous and often long text data into concise but coherent and informative summaries for efficient human consumption. Despite…
Pre-trained and fine-tuned news summarizers are expected to generalize to news articles unseen in the fine-tuning (training) phase. However, these articles often contain specifics, such as new events and people, a summarizer could not learn…
This study presents a controllable abstract summary generation method for large language models based on prompt engineering. To address the issues of summary quality and controllability in traditional methods, we design a multi-stage prompt…
Risk mining technologies seek to find relevant textual extractions that capture entity-risk relationships. However, when high volume data sets are processed, a multitude of relevant extractions can be returned, shifting the focus to how…
Due to the exponential growth of information and the need for efficient information consumption the task of summarization has gained paramount importance. Evaluating summarization accurately and objectively presents significant challenges,…
A quality abstractive summary should not only copy salient source texts as summaries but should also tend to generate new conceptual words to express concrete details. Inspired by the popular pointer generator sequence-to-sequence model,…
Hallucination is a known issue for neural abstractive summarization models. Recent work suggests that the degree of hallucination may depend on errors in the training data. In this work, we propose a new method called Contrastive Parameter…
This study addresses the reliability of automatic summarization in high-risk scenarios and proposes a large language model framework that integrates uncertainty quantification and risk-aware mechanisms. Starting from the demands of…
Unsupervised extractive summarization aims to extract salient sentences from a document as the summary without labeled data. Recent literatures mostly research how to leverage sentence similarity to rank sentences in the order of salience.…
Natural Language Processing is booming with its applications in the real world, one of which is Text Summarization for large texts including news articles. This research paper provides an extensive comparative evaluation of extractive and…
Automatic summarization generates concise summaries that contain key ideas of source documents. As the most mainstream datasets for the news sub-domain, CNN/DailyMail and BBC XSum have been widely used for performance benchmarking. However,…
State-of-the-art abstractive summarization systems frequently hallucinate content that is not supported by the source document, mainly due to noise in the training dataset. Existing methods opt to drop the noisy samples or tokens from the…
Summarizing texts is not a straightforward task. Before even considering text summarization, one should determine what kind of summary is expected. How much should the information be compressed? Is it relevant to reformulate or should the…
A typical journalistic convention in news articles is to deliver the most salient information in the beginning, also known as the lead bias. While this phenomenon can be exploited in generating a summary, it has a detrimental effect on…
Existing summarization systems mostly generate summaries purely relying on the content of the source document. However, even for humans, we usually need some references or exemplars to help us fully understand the source document and write…
Abstractive document summarization is usually modeled as a sequence-to-sequence (Seq2Seq) learning problem. Unfortunately, training large Seq2Seq based summarization models on limited supervised summarization data is challenging. This paper…
Neural abstractive summarization has been studied in many pieces of literature and achieves great success with the aid of large corpora. However, when encountering novel tasks, one may not always benefit from transfer learning due to the…
Due to the subjectivity of the summarization, it is a good practice to have more than one gold summary for each training document. However, many modern large-scale abstractive summarization datasets have only one-to-one samples written by…
A commonly observed problem with the state-of-the art abstractive summarization models is that the generated summaries can be factually inconsistent with the input documents. The fact that automatic summarization may produce…
Training abstractive summarization models typically requires large amounts of data, which can be a limitation for many domains. In this paper we explore using domain transfer and data synthesis to improve the performance of recent…