Related papers: Improving the Robustness of Summarization Models b…

State-of-the-art summarization systems are trained and evaluated on massive datasets scraped from the web. Despite their prevalence, we know very little about the underlying characteristics (data noise, summarization complexity, etc.) of…

A robust summarization system should be able to capture the gist of the document, regardless of the specific word choices or noise in the input. In this work, we first explore the summarization models' robustness against perturbations…

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…

We propose a simple method for post-processing the outputs of a text summarization system in order to refine its overall quality. Our approach is to train text-to-text rewriting models to correct information redundancy errors that may arise…

Noise is a fundamental problem in learning theory with huge effects in the application of Machine Learning (ML) methods, due to real world data tendency to be noisy. Additionally, introduction of malicious noise can make ML methods fail…

We propose a unified model combining the strength of extractive and abstractive summarization. On the one hand, a simple extractive model can obtain sentence-level attention with high ROUGE scores but less readable. On the other hand, a…

Neural network models have shown excellent fluency and performance when applied to abstractive summarization. Many approaches to neural abstractive summarization involve the introduction of significant inductive bias, exemplified through…

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…

Our analysis of large summarization datasets indicates that redundancy is a very serious problem when summarizing long documents. Yet, redundancy reduction has not been thoroughly investigated in neural summarization. In this work, we…

Neural abstractive summarization methods often require large quantities of labeled training data. However, labeling large amounts of summarization data is often prohibitive due to time, financial, and expertise constraints, which has…

Abstractive text summarization aims to shorten long text documents into a human readable form that contains the most important facts from the original document. However, the level of actual abstraction as measured by novel phrases that do…

Dialogue summarization task involves summarizing long conversations while preserving the most salient information. Real-life dialogues often involve naturally occurring variations (e.g., repetitions, hesitations) and existing dialogue…

Abstractive summarization approaches based on Reinforcement Learning (RL) have recently been proposed to overcome classical likelihood maximization. RL enables to consider complex, possibly non-differentiable, metrics that globally assess…

The supervised training of high-capacity models on large datasets containing hundreds of thousands of document-summary pairs is critical to the recent success of deep learning techniques for abstractive summarization. Unfortunately, in most…

Neural machine translation systems typically are trained on curated corpora and break when faced with non-standard orthography or punctuation. Resilience to spelling mistakes and typos, however, is crucial as machine translation systems are…

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…

In real-world scenarios with naturally occurring datasets, reference summaries are noisy and may contain information that cannot be inferred from the source text. On large news corpora, removing low quality samples has been shown to reduce…

Abstractive text summarization is a highly difficult problem, and the sequence-to-sequence model has shown success in improving the performance on the task. However, the generated summaries are often inconsistent with the source content in…

Sentence position is a strong feature for news summarization, since the lead often (but not always) summarizes the key points of the article. In this paper, we show that recent neural systems excessively exploit this trend, which although…

Text summarization condenses a text to a shorter version while retaining the important informations. Abstractive summarization is a recent development that generates new phrases, rather than simply copying or rephrasing sentences within the…