The advent of self-attention mechanisms within Transformer models has significantly propelled the advancement of deep learning algorithms,yielding outstanding achievements across diverse domains.Nonetheless,self-atten...The advent of self-attention mechanisms within Transformer models has significantly propelled the advancement of deep learning algorithms,yielding outstanding achievements across diverse domains.Nonetheless,self-attention mechanisms falter when applied to datasets with intricate semantic content and extensive dependency structures.In response,this paper introduces a Diffusion Sampling and Label-Driven Co-attention Neural Network(DSLD),which adopts a diffusion sampling method to capture more comprehensive semantic information of the data.Additionally,themodel leverages the joint correlation information of labels and data to introduce the computation of text representation,correcting semantic representationbiases in thedata,andincreasing the accuracyof semantic representation.Ultimately,the model computes the corresponding classification results by synthesizing these rich data semantic representations.Experiments on seven benchmark datasets show that our proposed model achieves competitive results compared to state-of-the-art methods.展开更多
Head-driven statistical models for natural language parsing are the most representative lexicalized syntactic parsing models, but they only utilize semantic dependency between words, and do not incorporate other seman...Head-driven statistical models for natural language parsing are the most representative lexicalized syntactic parsing models, but they only utilize semantic dependency between words, and do not incorporate other semantic information such as semantic collocation and semantic category. Some improvements on this distinctive parser are presented. Firstly, "valency" is an essential semantic feature of words. Once the valency of word is determined, the collocation of the word is clear, and the sentence structure can be directly derived. Thus, a syntactic parsing model combining valence structure with semantic dependency is purposed on the base of head-driven statistical syntactic parsing models. Secondly, semantic role labeling(SRL) is very necessary for deep natural language processing. An integrated parsing approach is proposed to integrate semantic parsing into the syntactic parsing process. Experiments are conducted for the refined statistical parser. The results show that 87.12% precision and 85.04% recall are obtained, and F measure is improved by 5.68% compared with the head-driven parsing model introduced by Collins.展开更多
The NOTHING ELSE food label, created at the Auckland University of Technology, lists the eight or less easily recognized ingredients on the front-of-pack within a circular band. This report describes the evolution of ...The NOTHING ELSE food label, created at the Auckland University of Technology, lists the eight or less easily recognized ingredients on the front-of-pack within a circular band. This report describes the evolution of the label into a stand-alone brand for products including nuts, dried fruit, biscuits and water sold in four cafes at the university. In partnership with an established food manufacturer a NOTHING ELSE healthier snackbar was developed and sold through the university fitness centres with sales being tracked electronically by time, day and quantity. Consumers/purchasers of this NOTHING ELSE bar were asked why they bought the bar and when they would eat it as well as if they would buy the bar again and why/why not. Two thirds of the 43 respondents said that they would buy the bar again. Three key reasons for repurchase were identified: taste (n = 12), “healthy” (n = 11) and “natural ingredients” (n = 10). Positive comments about the ingredients included: no additives or preservative, the low/no added sugar, and the presence of fibre demonstrating that this unique brand concept was meeting a consumer need for transparent product information. The next steps are commercial production of the snackbar and market expansion within the university.展开更多
基金the Communication University of China(CUC230A013)the Fundamental Research Funds for the Central Universities.
文摘The advent of self-attention mechanisms within Transformer models has significantly propelled the advancement of deep learning algorithms,yielding outstanding achievements across diverse domains.Nonetheless,self-attention mechanisms falter when applied to datasets with intricate semantic content and extensive dependency structures.In response,this paper introduces a Diffusion Sampling and Label-Driven Co-attention Neural Network(DSLD),which adopts a diffusion sampling method to capture more comprehensive semantic information of the data.Additionally,themodel leverages the joint correlation information of labels and data to introduce the computation of text representation,correcting semantic representationbiases in thedata,andincreasing the accuracyof semantic representation.Ultimately,the model computes the corresponding classification results by synthesizing these rich data semantic representations.Experiments on seven benchmark datasets show that our proposed model achieves competitive results compared to state-of-the-art methods.
基金Project(61262035) supported by the National Natural Science Foundation of ChinaProjects(GJJ12271,GJJ12742) supported by the Science and Technology Foundation of Education Department of Jiangxi Province,ChinaProject(20122BAB201033) supported by the Natural Science Foundation of Jiangxi Province,China
文摘Head-driven statistical models for natural language parsing are the most representative lexicalized syntactic parsing models, but they only utilize semantic dependency between words, and do not incorporate other semantic information such as semantic collocation and semantic category. Some improvements on this distinctive parser are presented. Firstly, "valency" is an essential semantic feature of words. Once the valency of word is determined, the collocation of the word is clear, and the sentence structure can be directly derived. Thus, a syntactic parsing model combining valence structure with semantic dependency is purposed on the base of head-driven statistical syntactic parsing models. Secondly, semantic role labeling(SRL) is very necessary for deep natural language processing. An integrated parsing approach is proposed to integrate semantic parsing into the syntactic parsing process. Experiments are conducted for the refined statistical parser. The results show that 87.12% precision and 85.04% recall are obtained, and F measure is improved by 5.68% compared with the head-driven parsing model introduced by Collins.
文摘The NOTHING ELSE food label, created at the Auckland University of Technology, lists the eight or less easily recognized ingredients on the front-of-pack within a circular band. This report describes the evolution of the label into a stand-alone brand for products including nuts, dried fruit, biscuits and water sold in four cafes at the university. In partnership with an established food manufacturer a NOTHING ELSE healthier snackbar was developed and sold through the university fitness centres with sales being tracked electronically by time, day and quantity. Consumers/purchasers of this NOTHING ELSE bar were asked why they bought the bar and when they would eat it as well as if they would buy the bar again and why/why not. Two thirds of the 43 respondents said that they would buy the bar again. Three key reasons for repurchase were identified: taste (n = 12), “healthy” (n = 11) and “natural ingredients” (n = 10). Positive comments about the ingredients included: no additives or preservative, the low/no added sugar, and the presence of fibre demonstrating that this unique brand concept was meeting a consumer need for transparent product information. The next steps are commercial production of the snackbar and market expansion within the university.
