Experiments in Newswire Summarisation

Abstract

Abstract. In this paper, we investigate extractive multi-document summarisation algorithms over newswire corpora. Examining recent findings, baseline algorithms, and state-of-the-art systems is pertinent given the current research interest in event tracking and summarisation. We first reproduce previous findings from the literature, validating that automatic summarisation evaluation is a useful proxy for manual evaluation, and validating that several state-of-the-art systems with similar automatic evaluation scores create different summaries from one another. Following this verification of previous findings, we then reimplement various baseline and state-of-the-art summarisation algorithms, and make several observations from our experiments. Our findings include: an optimised Lead baseline; indication that several standard baselines may be weak; evidence that the standard baselines can be improved; results showing that the most effective improved baselines are not statistically significantly less effective than the current state-of-the-art systems; and finally, observations that manually optimising the choice of anti-redundancy components, per topic, can lead to improvements in summarisation effectiveness.

HeadlineStanceChecker: Exploiting summarization to detect headline disinformation

“…The journalism field, and specifically the news domain, has been one of the most representative areas in which summarization has traditionally focused from the outset, partly thanks to the development of appropriate corpora (e.g. DUC, Gigaword, CNN/DailyMail) [63], and the wide range of techniques and approaches to help digest this type of information [64][65][66][67]. Besides the various summarization types that have been developed for this domain (single-document, multi-document, extractive, abstractive, generic, topic-oriented, etc.…”

CC-News-En

“…A basic "first-sentences" summarizer [10] was also employed, given that the opening paragraph of news articles generally provides an accurate and succinct overview of the article [35,40]. We refer to this option as the Intro summarizer.…”

Revisiting the Centroid-based Method: A Strong Baseline for Multi-Document Summarization

“…Rossiello et al (2017) improved the centroidbased method by representing sentences as sums of word embeddings instead of TF-IDF vectors so that semantic relationships between sentences that have no words in common can be captured. Mackie et al (2016) also evaluated summaries from SumRepo and did experiments on improving baseline systems such as the centroid-based and the KL-divergence method with different antiredundancy filters. Their best optimized baseline obtained a performance similar to the ICSI method in SumRepo.…”