Abstract
Extractive summarization has been the mainstay of automatic summarization for decades. Despite all the progress, extractive summarizers still suffer from shortcomings including coreference issues arising from extracting sentences away from their original context in the source document. This affects the coherence and readability of extractive summaries. In this work, we propose a lightweight post-editing step for extractive summaries that centers around a single linguistic decision: the definiteness of noun phrases. We conduct human evaluation studies that show that human expert judges substantially prefer the output of our proposed system over the original summaries. Moreover, based on an automatic evaluation study, we provide evidence for our system’s ability to generate linguistic decisions that lead to improved extractive summaries. We also draw insights about how the automatic system is exploiting some local cues related to the writing style of the main article texts or summary texts to make the decisions, rather than reasoning about the contexts pragmatically.
Highlights
Source Text: The school had to deal with a suspicious package received early in the morning
Original Extractive Summary: The school had to deal with a suspicious package received early in the morning
Post-Edited Pseudo-Extractive Summary: The school had to deal with a suspicious package received early in the morning
Summary
For the second step of predicting the definiteness of NPs, we adopt the methodology of Kabbara. Source Pre-trained Extractive Definiteness Modified Document Summarizer Summary Prediction Summary represent one of three classes: “the", “a" (or “an") and “none". Performance of different learning models on this task, we explore the use of a logistic regression. Sn} with n sentences, a a BERT-based (Devlin et al, 2019) neural model pre-trained extractive summarizer, f , generates a which has shown strong performance across a wide summary S = f (D) ⊂ D with the length of S be- range of NLP tasks (Rogers et al, 2020). The generated summary is passed to a post-editing step in which decisions are made regarding the definiteness of noun phrases (NPs). A definiteness prediction model g generates a modified summary S = g(S) which we refer to as pseudo-extractive summary.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
