scholarly journals Chinese Short Text Summary Generation Model Integrating Multi-Level Semantic Information

2018 ◽  
Author(s):  
Guanqin Chen
Keyword(s):  
Semantic Information ◽  
Generation Model ◽  
Short Text ◽  
Multi Level

Short Text Clustering Algorithms for Weibo Topic Detection

2014 ◽  
Vol 971-973 ◽  
pp. 1747-1751 ◽  
Author(s):  
Lei Zhang ◽  
Hai Qiang Chen ◽  
Wei Jie Li ◽  
Yan Zhao Liu ◽  
Run Pu Wu
Keyword(s):  
Text Analysis ◽  
Semantic Information ◽  
Clustering Algorithms ◽  
Text Clustering ◽  
Massive Data ◽  
Topic Detection ◽  
Clustering Methods ◽  
Short Text ◽  
Short Text Clustering ◽  
Application Requirements

Text clustering is a popular research topic in the field of text mining, and now there are a lot of text clustering methods catering to different application requirements. Currently, Weibo data acquisition is through the API provided by big microblogging platforms. In this essay, we will discuss the algorithm of extracting popular topics posted by Weibo users by text clustering after massive data collection. Due to the fact that traditional text analysis may not be applicable to short texts used in Weibo, text clustering shall be carried out through combining multiple posts into long texts, based on their features (forwards, comments and followers, etc.). Either frequency-based or density-based short text clustering can deliver in most cases. The former is applicable to find hot topics from large Weibo short texts, and the latter is applicable to find abnormal contents. Both the two methods use semantic information to improve the accuracy of clustering. Besides, they improve the performance of clustering through the parallelism.

scholarly journals Generating Multiple Diverse Responses for Short-Text Conversation

2019 ◽  
Vol 33 ◽  
pp. 6383-6390 ◽  
Author(s):  
Jun Gao ◽  
Wei Bi ◽  
Xiaojiang Liu ◽  
Junhui Li ◽  
Shuming Shi
Keyword(s):  
Reinforcement Learning ◽  
Learning Algorithm ◽  
Generative Models ◽  
Generation Model ◽  
Multiple Responses ◽  
Short Text ◽  
Output Response ◽  
Model Experiments ◽  
Reinforcement Learning Algorithm

Neural generative models have become popular and achieved promising performance on short-text conversation tasks. They are generally trained to build a 1-to-1 mapping from the input post to its output response. However, a given post is often associated with multiple replies simultaneously in real applications. Previous research on this task mainly focuses on improving the relevance and informativeness of the top one generated response for each post. Very few works study generating multiple accurate and diverse responses for the same post. In this paper, we propose a novel response generation model, which considers a set of responses jointly and generates multiple diverse responses simultaneously. A reinforcement learning algorithm is designed to solve our model. Experiments on two short-text conversation tasks validate that the multiple responses generated by our model obtain higher quality and larger diversity compared with various state-ofthe-art generative models.

scholarly journals Cognitive Aspects-Based Short Text Representation with Named Entity, Concept and Knowledge

2020 ◽  
Vol 10 (14) ◽  
pp. 4893 ◽  
Author(s):  
Wenfeng Hou ◽  
Qing Liu ◽  
Longbing Cao
Keyword(s):  
Text Classification ◽  
Semantic Representation ◽  
Semantic Features ◽  
Text Representation ◽  
Short Text ◽  
Individual Level ◽  
Named Entity ◽  
Concept Knowledge ◽  
Representation Model ◽  
Multi Level

Short text is widely seen in applications including Internet of Things (IoT). The appropriate representation and classification of short text could be severely disrupted by the sparsity and shortness of short text. One important solution is to enrich short text representation by involving cognitive aspects of text, including semantic concept, knowledge, and category. In this paper, we propose a named Entity-based Concept Knowledge-Aware (ECKA) representation model which incorporates semantic information into short text representation. ECKA is a multi-level short text semantic representation model, which extracts the semantic features from the word, entity, concept and knowledge levels by CNN, respectively. Since word, entity, concept and knowledge entity in the same short text have different cognitive informativeness for short text classification, attention networks are formed to capture these category-related attentive representations from the multi-level textual features, respectively. The final multi-level semantic representations are formed by concatenating all of these individual-level representations, which are used for text classification. Experiments on three tasks demonstrate our method significantly outperforms the state-of-the-art methods.

scholarly journals Image Caption Generation Model Based on Object Detector

2018 ◽  
pp. 5-14
Author(s):  
Aghasi Poghosyan ◽  
Hakob Sarukhanyan
Keyword(s):  
Natural Language ◽  
Object Detection ◽  
Information Extraction ◽  
Semantic Information ◽  
Generation Model ◽  
Single Model ◽  
Detection Model ◽  
Generator Performance ◽  
Image Caption Generation ◽  
Image Caption

Automated semantic information extraction from the image is a difficult task. There are works, which can extract image caption or object names and their coordinates. This work presents object detection and automated caption generation implemented via a single model. We have built an image caption generation model on top of object detection model. We have added extra layers on object detector to increase caption generator performance. We have developed a single model that can detect objects, localize them and generate image caption via natural language.

scholarly journals Commonsense Knowledge Aware Conversation Generation with Graph Attention

2018 ◽  
Author(s):  
Hao Zhou ◽  
Tom Young ◽  
Minlie Huang ◽  
Haizhou Zhao ◽  
Jingfang Xu ◽  
...  
Keyword(s):  
Language Processing ◽  
Large Scale ◽  
Semantic Information ◽  
Attention Mechanism ◽  
Generation Model ◽  
Dynamic Graph ◽  
Commonsense Knowledge ◽  
Word Generation ◽  
Proposed Model ◽  
Knowledge Graphs

Commonsense knowledge is vital to many natural language processing tasks. In this paper, we present a novel open-domain conversation generation model to demonstrate how large-scale commonsense knowledge can facilitate language understanding and generation. Given a user post, the model retrieves relevant knowledge graphs from a knowledge base and then encodes the graphs with a static graph attention mechanism, which augments the semantic information of the post and thus supports better understanding of the post. Then, during word generation, the model attentively reads the retrieved knowledge graphs and the knowledge triples within each graph to facilitate better generation through a dynamic graph attention mechanism. This is the first attempt that uses large-scale commonsense knowledge in conversation generation. Furthermore, unlike existing models that use knowledge triples (entities) separately and independently, our model treats each knowledge graph as a whole, which encodes more structured, connected semantic information in the graphs. Experiments show that the proposed model can generate more appropriate and informative responses than state-of-the-art baselines. 

scholarly journals Exploring Formation Mechanism of Medical Collaborative Practices in Multi-level Market from an Infra-marginal Perspective

2021 ◽  
Author(s):  
Sufen Wang
Keyword(s):  
Role Models ◽  
Equilibrium Analysis ◽  
Medical Services ◽  
Generation Model ◽  
Role Identities ◽  
Collaborative Practices ◽  
Single Level ◽  
Multi Level ◽  
The Government ◽  
The Stability

Abstract Purpose: The purpose of this paper to explore a set of methods to formally display and analyze the nature and laws of the emergence and evolution of all kinds of medical collaborative practices (MCPs) within multi-level market.Methodology: Based on Yang’s neoclassical economics, the paper argues that the reason for the origin of MCPs with multi-level market is the division of labor for different medical services and medical transaction service. From an infra-marginal perspective, the study processes are (1) to build a role generation model for collaborators. (2) to determine the role boundaries of collaborators by calculating the corner solution, and formalize the entanglement between role identities and specific MCPs through the corner equilibrium analysis. (3) to evaluate the stability of different forms of MCPs by general equilibrium analysis, and analyze their possible evolutionary paths of various MCPs by sensitivity analysis of the stability conditions of different structures. Results: (1) A role generation model of "producer-consumer", which is composed of three functions and involves three economic parameters, reflects the coexistence of division and cooperation, and integrate the influencing factors with process views. (2) The paper extracts eight role models and six structures of MCPs with corner equilibrium, and further formalizes the different ways of legalization of specific role identities in different MCPs in no market, or single-level or multi-level market. (3) Three structures (structure A with no market, structure CN with single-level market and structure CC with two-level market) have global equilibrium in different parameter spaces. With the increase of learning cost of medical services and medical transaction services, there are two structural evolution paths more likely to occur: " A - >CN -> CC " and "CN -> CC ->A".Conclusions: The research will provide theoretical basis for the government to select, formulate and implement the relevant policies of specific MCP, and help IT companies better develop internet medical service transaction platforms.

Sign in / Sign up

Export Citation Format

Share Document