Enhancing Semantic Understanding with Self-supervised Methods for Abstractive Dialogue Summarization

TL;DR

This paper introduces self-supervised techniques to improve dialogue summarization by enhancing BERT's contextual understanding, leading to better abstractive summaries on dialogue datasets.

Contribution

It proposes novel self-supervised methods to train dialogue-specific BERT models, addressing the gap in dialogue summarization compared to news article summarization.

Findings

Improved ROUGE scores on SAMSum dataset

Self-supervised methods enhance BERT's contextualization in dialogues

Sensitivity analysis identifies key hyperparameters

Abstract

Contextualized word embeddings can lead to state-of-the-art performances in natural language understanding. Recently, a pre-trained deep contextualized text encoder such as BERT has shown its potential in improving natural language tasks including abstractive summarization. Existing approaches in dialogue summarization focus on incorporating a large language model into summarization task trained on large-scale corpora consisting of news articles rather than dialogues of multiple speakers. In this paper, we introduce self-supervised methods to compensate shortcomings to train a dialogue summarization model. Our principle is to detect incoherent information flows using pretext dialogue text to enhance BERT's ability to contextualize the dialogue text representations. We build and fine-tune an abstractive dialogue summarization model on a shared encoder-decoder architecture using the enhanced BERT. We empirically evaluate our abstractive dialogue summarizer with the SAMSum corpus, a recently introduced dataset with abstractive dialogue summaries. All of our methods have contributed improvements to abstractive summary measured in ROUGE scores. Through an extensive ablation study, we also present a sensitivity analysis to critical model hyperparameters, probabilities of switching utterances and masking interlocutors.