SATS: simplification aware text summarization of scientific documents.

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.

Social mining for sustainable cities: thematic study of gender-based violence coverage in news articles and domestic violence in relation to COVID-19.

We argue that social computing and its diverse applications can contribute to the attainment of sustainable development goals (SDGs)-specifically to the SDGs concerning gender equality and empowerment of all women and girls, and to make cities and human settlements inclusive. To achieve the above goals for the sustainable growth of societies, it is crucial to study gender-based violence (GBV) in a smart city context, which is a common component of violence across socio-economic groups globally. This paper analyzes the nature of news articles reported in English newspapers of Pakistan, India, and the UK-accumulating 12,693 gender-based violence-related news articles. For the qualitative textual analysis, we employ Latent Dirichlet allocation for topic modeling and propose a Doc2Vec based word-embeddings model to classify gender-based violence-related content, called GBV2Vec. Further, by leveraging GBV2Vec, we also build an online tool that analyzes the sensitivity of Gender-based violence-related content from the textual data. We run a case study on GBV concerning COVID-19 by feeding the data collected through Google News API. Finally, we show different news reporting trends and the nature of the gender-based violence committed during the testing times of COVID-19. The approach and the toolkit that this paper proposes will be of great value to decision-makers and human rights activists, given the prompt and coordinated performance against gender-based violence in smart city context-and can contribute to the achievement of SDGs for sustainable growth of human societies.

Detailed analysis of Ethereum network on transaction behavior, community structure and link prediction.

Ethereum, the second-largest cryptocurrency after Bitcoin, has attracted wide attention in the last few years and accumulated significant transaction records. However, the underlying Ethereum network structure is still relatively unexplored. Also, very few attempts have been made to perform link predictability on the Ethereum transactions network. This paper presents a Detailed Analysis of the Ethereum Network on Transaction Behavior, Community Structure, and Link Prediction (DANET) framework to investigate various valuable aspects of the Ethereum network. Specifically, we explore the change in wealth distribution and accumulation on Ethereum Featured Transactional Network (EFTN) and further study its community structure. We further hunt for a suitable link predictability model on EFTN by employing state-of-the-art Variational Graph Auto-Encoders. The link prediction experimental results demonstrate the superiority of outstanding prediction accuracy on Ethereum networks. Moreover, the statistic usages of the Ethereum network are visualized and summarized through the experiments allowing us to formulate conjectures on the current use of this technology and future development.

Anti-inflammatory effects of Trigonella gharuensis: Comparative analysis in BALB/C mouse model.

Plants are extensively used in treating inflammatory disorders. The current study focused on evaluating anti-inflammatory potential of Trigonella gharuensis. The ethanolic and n-hexane extracts of T. gharuensis were given orally at the dose of 400mg/kg/day. Various in vivo inflammatory models such as carrageenan-, histamine-, dextran- and serotonin-induced paw edemas; xylene-induced ear edema, and castor oil-induced diarrhea models were used for validation of different mechanisms of autacoid inhibition. Gas chromatography-mass spectrometry analyses were performed to find out compounds responsible for anti-inflammatory properties. Both extracts significantly inhibited (P<0.05) carrageenan-, histamine-, dextran- and serotonin-induced paw edema in early and late acute inflammation phases. Suppression of xylene-induced ear edema supported suggested inhibition of autacoids. Attenuation of castor oil-induced diarrhea suggested prostaglandin inhibition by both extracts and supported inhibition of carrageenan-induced inflammation in the late phase. GC-MS analysis indicated constituents with considerable biological activities such as, saturated and unsaturated fatty acid esters, coumarins, terpenes, and aromatic and aliphatic compounds in the extracts. In conclusion, extracts of T. gharuensis possess significant anti-inflammatory activity which might be ascribed to the inhibition of autacoids.