Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Domain-specific Guided Summarization for Mental Health Posts

Lu Qian, Yuqi Wang, Zimu Wang, Haiyang Zhang, Wei Wang, Ting Yu, Anh Nguyen

TL;DR

A guided summarizer equipped with a dual-encoder and an adapted decoder that utilizes novel domain-specific guidance signals to enhance its capacity to align closely with the content and context of guidance, thereby generating a domain-relevant summary.

Abstract

In domain-specific contexts, particularly mental health, abstractive summarization requires advanced techniques adept at handling specialized content to generate domain-relevant and faithful summaries. In response to this, we introduce a guided summarizer equipped with a dual-encoder and an adapted decoder that utilizes novel domain-specific guidance signals, i.e., mental health terminologies and contextually rich sentences from the source document, to enhance its capacity to align closely with the content and context of guidance, thereby generating a domain-relevant summary. Additionally, we present a post-editing correction model to rectify errors in the generated summary, thus enhancing its consistency with the original content in detail. Evaluation on the MentSum dataset reveals that our model outperforms existing baseline models in terms of both ROUGE and FactCC scores. Although the experiments are specifically designed for mental health posts, the methodology we've developed offers broad applicability, highlighting its versatility and effectiveness in producing high-quality domain-specific summaries.

Domain-specific Guided Summarization for Mental Health Posts

TL;DR

A guided summarizer equipped with a dual-encoder and an adapted decoder that utilizes novel domain-specific guidance signals to enhance its capacity to align closely with the content and context of guidance, thereby generating a domain-relevant summary.

Abstract

In domain-specific contexts, particularly mental health, abstractive summarization requires advanced techniques adept at handling specialized content to generate domain-relevant and faithful summaries. In response to this, we introduce a guided summarizer equipped with a dual-encoder and an adapted decoder that utilizes novel domain-specific guidance signals, i.e., mental health terminologies and contextually rich sentences from the source document, to enhance its capacity to align closely with the content and context of guidance, thereby generating a domain-relevant summary. Additionally, we present a post-editing correction model to rectify errors in the generated summary, thus enhancing its consistency with the original content in detail. Evaluation on the MentSum dataset reveals that our model outperforms existing baseline models in terms of both ROUGE and FactCC scores. Although the experiments are specifically designed for mental health posts, the methodology we've developed offers broad applicability, highlighting its versatility and effectiveness in producing high-quality domain-specific summaries.

Paper Structure

This paper contains 32 sections, 2 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Guided Abstractive Summarization
  4. Domain-specific Summarization
  5. Methodology
  6. Guided Summarizer
  7. Domain-specific Guidance Signal.
  8. Dual-encoders.
  9. Decoder.
  10. Training Objective.
  11. Corrector
  12. Artificial Corruption Data.
  13. Model Design.
  14. Experiments
  15. Dataset
  16. ...and 17 more sections

Figures (2)

  • Figure 1: This example highlights the importance of an ideal summary that, compared to a general summary, is focused on domain relevance and faithful to the source post, providing essential support for effective communication within the mental health community.
  • Figure 2: The overall architecture: The initial phase involves a guided summarizer with a dual-encoder and an adapted decoder architecture, utilizing domain-specific guidance signals to produce a candidate summary. This is then refined in the second phase by a post-editing corrector, which identifies and corrects potential inconsistencies in the candidate summary with respect to the source document.