Conditional Neural Generation using Sub-Aspect Functions for Extractive News Summarization

04/29/2020
by   Zhengyuan Liu, et al.
0

Much progress has been made in text summarization, fueled by neural architectures using large-scale training corpora. However, reference summaries tend to be position-biased and constructed in an under-constrained fashion, especially for benchmark datasets in the news domain. We propose a neural framework that can flexibly control which sub-aspect functions (i.e. importance, diversity, position) to focus on during summary generation. We demonstrate that automatically extracted summaries with minimal position bias can achieve performance at least equivalent to standard models that take advantage of position bias. We also show that news summaries generated with a focus on diversity can be more preferred by human raters. These results suggest that a more flexible neural summarization framework can provide more control options to tailor to different application needs. This framework is useful because it is often difficult to know or articulate a priori what the user-preferences of certain applications are.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/30/2019

Earlier Isn't Always Better: Sub-aspect Analysis on Corpus and System Biases in Summarization

Despite the recent developments on neural summarization systems, the und...
research
12/17/2017

Query-Based Abstractive Summarization Using Neural Networks

In this paper, we present a model for generating summaries of text docum...
research
02/16/2023

Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization

Text summarization has been a crucial problem in natural language proces...
research
10/24/2022

LANS: Large-scale Arabic News Summarization Corpus

Text summarization has been intensively studied in many languages, and s...
research
07/27/2012

Diversity in Ranking using Negative Reinforcement

In this paper, we consider the problem of diversity in ranking of the no...
research
05/03/2023

Characterizing Political Bias in Automatic Summaries: A Case Study of Trump and Biden

Growing literature has shown that powerful NLP systems may encode social...
research
04/02/2022

Improving the Factual Accuracy of Abstractive Clinical Text Summarization using Multi-Objective Optimization

While there has been recent progress in abstractive summarization as app...

Please sign up or login with your details

Forgot password? Click here to reset