KLearn: Background Knowledge Inference from Summarization Data

10/13/2020
by   Maxime Peyrard, et al.
0

The goal of text summarization is to compress documents to the relevant information while excluding background information already known to the receiver. So far, summarization researchers have given considerably more attention to relevance than to background knowledge. In contrast, this work puts background knowledge in the foreground. Building on the realization that the choices made by human summarizers and annotators contain implicit information about their background knowledge, we develop and compare techniques for inferring background knowledge from summarization data. Based on this framework, we define summary scoring functions that explicitly model background knowledge, and show that these scoring functions fit human judgments significantly better than baselines. We illustrate some of the many potential applications of our framework. First, we provide insights into human information importance priors. Second, we demonstrate that averaging the background knowledge of multiple, potentially biased annotators or corpora greatly improves summary-scoring performance. Finally, we discuss potential applications of our framework beyond summarization.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/26/2018

Tone Biased MMR Text Summarization

Text summarization is an interesting area for researchers to develop new...
research
04/13/2020

AREDSUM: Adaptive Redundancy-Aware Iterative Sentence Ranking for Extractive Document Summarization

Redundancy-aware extractive summarization systems score the redundancy o...
research
10/25/2022

Universal Evasion Attacks on Summarization Scoring

The automatic scoring of summaries is important as it guides the develop...
research
05/19/2023

IKDSumm: Incorporating Key-phrases into BERT for extractive Disaster Tweet Summarization

Online social media platforms, such as Twitter, are one of the most valu...
research
05/14/2021

EASE: Extractive-Abstractive Summarization with Explanations

Current abstractive summarization systems outperform their extractive co...
research
08/03/2022

Mutual Information Scoring: Increasing Interpretability in Categorical Clustering Tasks with Applications to Child Welfare Data

Youth in the American foster care system are significantly more likely t...
research
05/03/2023

Background Knowledge Grounding for Readable, Relevant, and Factual Biomedical Lay Summaries

Communication of scientific findings to the public is important for keep...

Please sign up or login with your details

Forgot password? Click here to reset