Generating Summaries with Controllable Readability Levels

• URL: http://arxiv.org/abs/2310.10623v1
• Date: Mon, 16 Oct 2023 17:46:26 GMT
• Title: Generating Summaries with Controllable Readability Levels
• Authors: Leonardo F. R. Ribeiro, Mohit Bansal, Markus Dreyer
• Abstract summary: Several factors affect the readability level, such as the complexity of the text, its subject matter, and the reader's background knowledge. Current text generation approaches lack refined control, resulting in texts that are not customized to readers' proficiency levels. We develop three text generation techniques for controlling readability: instruction-based readability control, reinforcement learning to minimize the gap between requested and observed readability, and a decoding approach that uses look-ahead to estimate the readability of upcoming decoding steps.
• Score: 67.34087272813821
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Readability refers to how easily a reader can understand a written text. Several factors affect the readability level, such as the complexity of the text, its subject matter, and the reader's background knowledge. Generating summaries based on different readability levels is critical for enabling knowledge consumption by diverse audiences. However, current text generation approaches lack refined control, resulting in texts that are not customized to readers' proficiency levels. In this work, we bridge this gap and study techniques to generate summaries at specified readability levels. Unlike previous methods that focus on a specific readability level (e.g., lay summarization), we generate summaries with fine-grained control over their readability. We develop three text generation techniques for controlling readability: (1) instruction-based readability control, (2) reinforcement learning to minimize the gap between requested and observed readability and (3) a decoding approach that uses lookahead to estimate the readability of upcoming decoding steps. We show that our generation methods significantly improve readability control on news summarization (CNN/DM dataset), as measured by various readability metrics and human judgement, establishing strong baselines for controllable readability in summarization.

Related papers

• Analysing Zero-Shot Readability-Controlled Sentence Simplification [54.09069745799918]
  We investigate how different types of contextual information affect a model's ability to generate sentences with the desired readability. Results show that all tested models struggle to simplify sentences due to models' limitations and characteristics of the source sentences. Our experiments also highlight the need for better automatic evaluation metrics tailored to RCTS.
  arXiv  Detail & Related papers  (2024-09-30T12:36:25Z)
• Free-text Rationale Generation under Readability Level Control [6.338124510580766]
  We investigate how large language models (LLMs) perform rationale generation under the effects of readability level control. We find that explanations are adaptable to such instruction, though the requested readability is often misaligned with the measured text complexity. Our human annotators confirm a generally satisfactory impression on rationales at all readability levels.
  arXiv  Detail & Related papers  (2024-07-01T15:34:17Z)
• Automating Easy Read Text Segmentation [2.7309692684728617]
  Easy Read text is one of the main forms of access to information for people with reading difficulties. One of the key characteristics of this type of text is the requirement to split sentences into smaller grammatical segments. We study novel methods for the task, leveraging masked and generative language models, along with constituent parsing.
  arXiv  Detail & Related papers  (2024-06-17T12:25:25Z)
• Is it Possible to Modify Text to a Target Readability Level? An Initial Investigation Using Zero-Shot Large Language Models [2.913033886371052]
  We propose a novel readability-controlled text modification task. The task requires the generation of 8 versions at various target readability levels for each input text. We find greater drops in semantic and lexical similarity between the source and target texts with greater shifts in the readability.
  arXiv  Detail & Related papers  (2023-09-22T00:47:18Z)
• Informative Text Generation from Knowledge Triples [56.939571343797304]
  We propose a novel memory augmented generator that employs a memory network to memorize the useful knowledge learned during the training. We derive a dataset from WebNLG for our new setting and conduct extensive experiments to investigate the effectiveness of our model.
  arXiv  Detail & Related papers  (2022-09-26T14:35:57Z)
• Readability Research: An Interdisciplinary Approach [62.03595526230364]
  We aim to provide a firm foundation for readability research, a comprehensive framework for readability research. Readability refers to aspects of visual information design which impact information flow from the page to the reader. These aspects can be modified on-demand, instantly improving the ease with which a reader can process and derive meaning from text.
  arXiv  Detail & Related papers  (2021-07-20T16:52:17Z)
• Predicting Text Readability from Scrolling Interactions [6.530293714772306]
  This paper investigates how scrolling behaviour relates to the readability of a text. We make our dataset publicly available and show that there are statistically significant differences in the way readers interact with text depending on the text level.
  arXiv  Detail & Related papers  (2021-05-13T15:27:00Z)
• Hierarchical Bi-Directional Self-Attention Networks for Paper Review Rating Recommendation [81.55533657694016]
  We propose a Hierarchical bi-directional self-attention Network framework (HabNet) for paper review rating prediction and recommendation. Specifically, we leverage the hierarchical structure of the paper reviews with three levels of encoders: sentence encoder (level one), intra-review encoder (level two) and inter-review encoder (level three) We are able to identify useful predictors to make the final acceptance decision, as well as to help discover the inconsistency between numerical review ratings and text sentiment conveyed by reviewers.
  arXiv  Detail & Related papers  (2020-11-02T08:07:50Z)
• Salience Estimation with Multi-Attention Learning for Abstractive Text Summarization [86.45110800123216]
  In the task of text summarization, salience estimation for words, phrases or sentences is a critical component. We propose a Multi-Attention Learning framework which contains two new attention learning components for salience estimation.
  arXiv  Detail & Related papers  (2020-04-07T02:38:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.