ﻻ يوجد ملخص باللغة العربية
Pre-trained neural abstractive summarization systems have dominated extractive strategies on news summarization performance, at least in terms of ROUGE. However, system-generated abstractive summaries often face the pitfall of factual inconsistency: generating incorrect facts with respect to the source text. To address this challenge, we propose Span-Fact, a suite of two factual correction models that leverages knowledge learned from question answering models to make corrections in system-generated summaries via span selection. Our models employ single or multi-masking strategies to either iteratively or auto-regressively replace entities in order to ensure semantic consistency w.r.t. the source text, while retaining the syntactic structure of summaries generated by abstractive summarization models. Experiments show that our models significantly boost the factual consistency of system-generated summaries without sacrificing summary quality in terms of both automatic metrics and human evaluation.
Neural abstractive summarization systems have achieved promising progress, thanks to the availability of large-scale datasets and models pre-trained with self-supervised methods. However, ensuring the factual consistency of the generated summaries fo
Community Question Answering (CQA) forums such as Stack Overflow and Yahoo! Answers contain a rich resource of answers to a wide range of questions. Each question thread can receive a large number of answers with different perspectives. The goal of m
A key challenge for abstractive summarization is ensuring factual consistency of the generated summary with respect to the original document. For example, state-of-the-art models trained on existing datasets exhibit entity hallucination, generating n
Sequence-to-sequence models provide a viable new approach to generative summarization, allowing models that are no longer limited to simply selecting and recombining sentences from the original text. However, these models have three drawbacks: their
Recently, various neural encoder-decoder models pioneered by Seq2Seq framework have been proposed to achieve the goal of generating more abstractive summaries by learning to map input text to output text. At a high level, such neural models can freel