Improving Abstractive Dialogue Summarization Using Keyword Extraction

Abstract

Abstractive dialogue summarization aims to generate a short passage that contains important content for a particular dialogue spoken by multiple speakers. In abstractive dialogue summarization systems, capturing the subject in the dialogue is challenging owing to the properties of colloquial texts. Moreover, the system often generates uninformative summaries. In this paper, we propose a novel keyword-aware dialogue summarization system (KADS) that easily captures the subject in the dialogue to alleviate the problem mentioned above through the efficient usage of keywords. Specifically, we first extract the keywords from the input dialogue using a pre-trained keyword extractor. Subsequently, KADS efficiently leverages the keywords information of the dialogue to the transformer-based dialogue system by using the pre-trained keyword extractor. Extensive experiments performed on three benchmark datasets show that the proposed method outperforms the baseline system. Additionally, we demonstrate that the proposed keyword-aware dialogue summarization system exhibits a high-performance gain in low-resource conditions where the number of training examples is highly limited.

Academic assistance chatbot-a comprehensive NLP and deep learning-based approaches

“…Keypoint-based summarization (KeyBERT) is a pre-trained model that uses BERT embeddings to extract the most relevant keywords or key phrases from a given document. KeyBERT is a powerful tool for summarizing text and can be used to generate topic names for articles, among other applications [46]. In this methodology, we will outline how to use the KeyBERT model to extract keywords to be used as a topic name for an article.…”

Multistage Mixed-Attention Unsupervised Keyword Extraction for Summary Generation

“…Summary generation is a task of text generation [1], and researchers use different techniques to generate summaries, including rewriting or extracting various information from documents [2]. Currently, lots of research results have been achieved in generating summaries for short texts [3,4]. However, it is still difficult to quickly obtain high-quality summaries from long textual data such as long documents, news interviews, and conference content.…”