STV-BEATS: Skip Thought Vector and Bi-Encoder based Automatic Text Summarizer

Tomer, Minakshi; Kumar, Manoj

doi:10.1016/j.knosys.2021.108108

Cited by 7 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Srivastava et al (2022) investigated an unsupervised extractive summarization approach that combined clustering with topic modelling to reduce topic bias. Tomer and Kumar (2022) proposed the STV-BEATS summarization framework, which uses skip-thought vectors to generate sentence-based embeddings and a long short-term memory (LSTM)-based deep autoencoder to reduce the dimensionality of the skip-thought vectors.…”

Section: Related Work 21 Text Summarization Approachesmentioning

confidence: 99%

Advanced intelligent health advice with informative summaries to facilitate treatment decision-making

Liu

Chen

2023

View full text Add to dashboard Cite

Purpose Whether automatically generated summaries of health social media can assist users in appropriately managing their diseases and ensuring better communication with health professionals becomes an important issue. This paper aims to develop a novel deep learning-based summarization approach for obtaining the most informative summaries from online patient reviews accurately and effectively. Design/methodology/approach This paper proposes a framework to generate summaries that integrates a domain-specific pre-trained embedding model and a deep neural extractive summary approach by considering content features, text sentiment, review influence and readability features. Representative health-related summaries were identified, and user judgements were analysed. Findings Experimental results on the three real-world health forum data sets indicate that awarding sentences without incorporating all the adopted features leads to declining summarization performance. The proposed summarizer significantly outperformed the comparison baseline. User judgement through the questionnaire provides realistic and concrete evidence of crucial features that remarkably influence patient forum review summaries. Originality/value This study contributes to health analytics and management literature by exploring users’ expressions and opinions through the health deep learning summarization model. The research also developed an innovative mindset to design summarization weighting methods from user-created content on health topics.

show abstract

Section: Related Work 21 Text Summarization Approachesmentioning

confidence: 99%

Advanced intelligent health advice with informative summaries to facilitate treatment decision-making

Liu

Chen

2023

View full text Add to dashboard Cite

show abstract

“…Skip-thought expands the skipgrams model beyond word embeddings to encompass sentence embeddings. Instead of forecasting context based on adjacent words, skip-thought anticipates the target sentence by considering both the preceding and subsequent sentences [15]. The global vector (GloVe) on the otherhand incorporates a global matrix factorization and local context window techniques through a bilinear regression model.…”

Section: What Are Embeddings and How Are They Generated?mentioning

confidence: 99%

Optimizing Sales Prediction in Online Grocery Shopping using Product Embeddings

Aziegbemhin

2023

Preprint

View full text Add to dashboard Cite

The focus of this research is to delve into the world of product embeddings and their potential to improve prediction accuracy. The study included a thorough review of existing literature to highlight the generation of embeddings and their utility in downstream tasks. This review uncovered the significance of embeddings in enhancing prediction accuracy, showing promise for their application in the realm of online grocery shopping. By employing embedding techniques, we aim to examine how they refine sales predictions, ultimately contributing to improved inventory management and optimized supply chain processes in the e-commerce domain. Future work will encompass data acquisition and a comprehensive process involving embedding generation, model training, and hyperparameter tuning to validate these findings.

show abstract

“…The automated generation of simplified summaries of scholarly articles is a popular mechanism for the public dissemination of scientific discoveries (Hou et al, 2022 ). This task can be performed by leveraging text summarization (Tomer and Kumar, 2022 ) and text simplification (Al-Thanyyan and Azmi, 2021 ), which are well-defined tasks in Natural Language Processing (NLP) (Iqbal et al, 2021 ). Text summarization is the task of reducing text size while maintaining the information presented in the text.…”

Section: Introductionmentioning

confidence: 99%

SATS: simplification aware text summarization of scientific documents

Zaman,

Kamiran,

Shardlow

et al. 2024

Front. Artif. Intell.

View full text Add to dashboard Cite

Simplifying summaries of scholarly publications has been a popular method for conveying scientific discoveries to a broader audience. While text summarization aims to shorten long documents, simplification seeks to reduce the complexity of a document. To accomplish these tasks collectively, there is a need to develop machine learning methods to shorten and simplify longer texts. This study presents a new Simplification Aware Text Summarization model (SATS) based on future n-gram prediction. The proposed SATS model extends ProphetNet, a text summarization model, by enhancing the objective function using a word frequency lexicon for simplification tasks. We have evaluated the performance of SATS on a recently published text summarization and simplification corpus consisting of 5,400 scientific article pairs. Our results in terms of automatic evaluation demonstrate that SATS outperforms state-of-the-art models for simplification, summarization, and joint simplification-summarization across two datasets on ROUGE, SARI, and CSS1. We also provide human evaluation of summaries generated by the SATS model. We evaluated 100 summaries from eight annotators for grammar, coherence, consistency, fluency, and simplicity. The average human judgment for all evaluated dimensions lies between 4.0 and 4.5 on a scale from 1 to 5 where 1 means low and 5 means high.

show abstract

STV-BEATS: Skip Thought Vector and Bi-Encoder based Automatic Text Summarizer

Cited by 7 publications

References 26 publications

Advanced intelligent health advice with informative summaries to facilitate treatment decision-making

Advanced intelligent health advice with informative summaries to facilitate treatment decision-making

Optimizing Sales Prediction in Online Grocery Shopping using Product Embeddings

SATS: simplification aware text summarization of scientific documents

Contact Info

Product

Resources

About