Who Speaks Like a Style of Vitamin: Towards Syntax-Aware Dialogue Summarization Using Multi-Task Learning

Lee, Seolhwa; Yang, Kisu; Park, Chanjun; Sedoc, João; Lim, Heuiseok

doi:10.1109/access.2021.3124556

Cited by 7 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Studies on multi-task learning have shown that solving different tasks in a simultaneous fashion often improves learning efficiency and performance, compared to models trained separately (Caruana, 1997). Future work could follow up on previous attempts in this direction (Li et al, 2019;Feng et al, 2021b;Lee et al, 2021). Factual consistency.…”

Section: Future Directionsmentioning

confidence: 94%

Abstractive Meeting Summarization: A Survey

Rennard¹,

Shang²,

Hunter³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recent advances in deep learning, and especially the invention of encoder-decoder architectures, has significantly improved the performance of abstractive summarization systems. While the majority of research has focused on written documents, we have observed an increasing interest in the summarization of dialogues and multi-party conversation over the past few years. A system that could reliably transform the audio or transcript of a human conversation into an abridged version that homes in on the most important points of the discussion would be valuable in a wide variety of real-world contexts, from business meetings to medical consultations to customer service calls. This paper focuses on abstractive summarization for multi-party meetings, providing a survey of the challenges, datasets and systems relevant to this task and a discussion of promising directions for future study.

show abstract

Section: Future Directionsmentioning

confidence: 94%

Abstractive Meeting Summarization: A Survey

Rennard¹,

Shang²,

Hunter³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…One of the simplest ways to tackle this task is to use the existing summarization systems trained on widely used datasets such as CNN/DM [4] or XSum [5]. However, different from generating a summary for well-structured documents such as news articles or academic papers, generating a summary for the given dialogue requires additional consideration to the properties of colloquial texts [6]. Among them, the most representative characteristic of the colloquial text is that it often consists of multiple utterances from multiple speakers.…”

Section: Introductionmentioning

confidence: 99%

Improving Abstractive Dialogue Summarization Using Keyword Extraction

Yoo,

Lee

2023

Applied Sciences

View full text Add to dashboard Cite

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.

show abstract

“…Certain recent studies undertook another approach to utilize auxiliary information to overcome the limitation of the content-based model [14], [19], [20]. In particular, user relationship information on social media and the news consuming behavior of users are represented as auxiliary information that surrounds news.…”

Section: Introductionmentioning

confidence: 99%

Utilization Strategy of User Engagements in Korean Fake News Detection

et al. 2022

Self Cite

View full text Add to dashboard Cite

Fake News (disinformation with malicious intent) has emerged as a major social problem. To address this issue, previous studies mainly utilized single information, the news content, to detect fake news. However, using only news content in training is insufficient. Moreover, most studies did not consider the propagation aspect of fake news as a training feature. Thus, in an attempt to incorporate the ability to learn representation based on textual information and social context, this study proposed a fake news detection algorithm that thoroughly utilizes user graph in Korean fake news and dataset construction methods. In addition, a training strategy was proposed for utilizing user graph in Korean fake news detection through comparative and ablation studies. The experimental results showed that K-FANG outperformed the baseline in detecting fake news. Moreover, user engagements were found to be useful for detecting fake news even if the data contained hate speech. Finally, the validity of using stance information by expanding its class and controlling the class imbalance issues was also verified. This study provided useful implications for utilizing user information in fake news detection.

show abstract

Who Speaks Like a Style of Vitamin: Towards Syntax-Aware Dialogue Summarization Using Multi-Task Learning

Cited by 7 publications

References 27 publications

Abstractive Meeting Summarization: A Survey

Abstractive Meeting Summarization: A Survey

Improving Abstractive Dialogue Summarization Using Keyword Extraction

Utilization Strategy of User Engagements in Korean Fake News Detection

Contact Info

Product

Resources

About