Measuring Similarity of Academic Articles with Semantic Profile and Joint Word Embedding

Long-document semantic measurement has great significance in many applications such as semantic searchs, plagiarism detection, and automatic technical surveys. However, research efforts have mainly focused on the semantic similarity of short texts. Document-level semantic measurement remains an open issue due to problems such as the omission of background knowledge and topic transition. In this paper, we propose a novel semantic matching method for long documents in the academic domain. To accurately represent the general meaning of an academic article, we construct a semantic profile in which key semantic elements such as the research purpose, methodology, and domain are included and enriched. As such, we can obtain the overall semantic similarity of two papers by computing the distance between their profiles. The distances between the concepts of two different semantic profiles are measured by word vectors. To improve the semantic representation quality of word vectors, we propose a joint word-embedding model for incorporating a domain-specific semantic relation constraint into the traditional context constraint. Our experimental results demonstrate that, in the measurement of document semantic similarity, our approach achieves substantial improvement over state-of-the-art methods, and our joint word-embedding model produces significantly better word representations than traditional word-embedding models.

Effect of microbial fermentation on the sensory characteristics and chemical compositions of Chinese sweet tea(Lithocarpus litseifolius(Hance)Chun)

Sweet tea,which has hundreds of years of use among in Chinese folk,is a traditional herbal tea with pleasant sweetness,bitterness and astringency.In the current study,we used traditional microbial fermentation to improve sensory characteristics of sweet tea,especially for the reduction of bitterness and astringency.The dynamic changes of non-volatile,volatile compounds and microbial community were investigated during microbial fermentation.The contents of polyphenols,flavonoids,soluble sugar,soluble protein,catechins and dihydrochalcones decreased significantly while the tea pigments,free amino acids and gallic acid content inversely increased during microbial fermentation.A total of 61 volatile compounds were identified and quantified in sweet tea,of which 20 key compounds were identified as odor active compounds(OAV),including 3 aldehydes,1 ketone,4 alcohols,9 esters,4 alkenes and 3 other compounds.In addition,eight fungi and four bacteria were considered as core microorganisms,such as Aspergillus,Alternaria,Cladosporium,Epicoccum,Itersonilia,Penicillium,Periconia,Wallemia,Aureimonas,Enterobacter,Klebsiella and Stenotrophomonas,which were significantly correlated with non-volatile compounds and flavor compounds.These results provided theoretical guidance for processing of fermented sweet tea.