下载文档原格式
文献信息Gleeson M. The study of B2C e-commerce sites in the countryside [J]. Procedia Computer Science, 2016, 12(3): 57-67.原文The study of B2C e-commerce sites in the countrysideGleeson M1 IntroductionB2C e-commerce is a pattern, which are usually said direct-to-consumer sales of products and services commercial retail mode. This form of electronic commerce general with network mostly retail, mainly by using the Internet to develop online sales activities. B2C namely enterprise through the Internet to provide consumers a new shopping environment - online stores, consumers through the network shopping on the Internet, online payment and other consumer behavior. A B2C business through the Internet offers consumers a new shopping environment - electronics store. Due to the rapid growth of the scale of rural, rural B2C e-commerce research also should pay attention to it.2 The development conditions of agricultural products B2C e-commerce2.1 Use e-commerce means the requestFirst of all, establish a systematic, professional, low-cost agricultural products logistics distribution system of agricultural products of short shelf life than other commodity, some consumer wants to buy the green food can storage, preservation and at the same time, consumption of agricultural products is characterized by the quantity of every time to buy, buy less frequency is high, the transaction amount is small. So there must be a quick, powerful agricultural products logistics distribution system. Second, perfect the system of B2C e-commerce of agricultural products. E-commerce development is very rapid, and electronic commerce is a kind of free, open trade mode, with the traditional business activities are quite different, some related management system, laws and regulations lag. So, how to guarantee the authenticity of online advertising and e-commerce market to crack down on illegal manufacturer, specification, agricultural market constraints become an important factor in thedevelopment of B2C e-commerce. Third, the wide application is order management subsystem. Agricultural product circulation enterprises must give the timely processing of orders for customers; arrange production according to the quantity of goods, all on schedule of delivery to the customer. Fourth is the establishment of operation mechanism of daily statistical pattern library. Agricultural products can be obtained at any time from the project manager of various kinds of statistical reports, pattern library, including all kinds of marketing mode, such as the advertising budget, new product planning, media selection, pricing models, the best marketing mix, etc., mainly for the senior management personnel in the face of the unstructured problems to provide a reference model.2.2 Requirements for agricultural product processing industryAgricultural production standardization, standardization of agricultural production, there are two aspects of content, namely certainty and uniformity. Agricultural products consumption dictionaries, dictionaries is the precondition for the development of B2C e-commerce, only the consumer to a certain extent, stray from the consumption habit of agricultural products, agricultural products and identity dictionaries, can from the Internet to buy agricultural products. Dictionaries contributed to the agricultural products of mass production of agricultural products, to create the possibility for standardization of agricultural production. Strengthen agricultural products between enterprises and engaged in distribution and other business cooperation. A higher percentage of the produce of the small and medium-sized enterprises, but also can't form the B2C e-commerce of agricultural products distribution system, it is difficult to achieve the rapid response. Joint, which requires companies to build and maintain a distribution system and thereby reducing costs play the role of the overall advantage.3 Key technology of rural electronic commerceFor rural electronic commerce has many problem presses for solution, such as agricultural preservation requires rapid logistics distribution (including dynamic path planning and convenient business matching and precise knowledge search, etc.), suitable for rural application environment of human-computer interaction need tosolve the problem of data open, etc.3.1 The dynamic path planningDynamic path planning problem about agricultural products distribution, due to the different characteristics of the agricultural products there is a big difference, so for different kinds of agricultural products, in addition to the need to consider when choosing a distribution model of general merchandise characteristics of constraints (such as demand, volume, delivery of the goods transportation cost, delivery time, vehicle capacity limits, mileage limit, time limit, etc.), also take into account the constraints of characteristic agricultural products (such as the efficiency of the agricultural products and transport the required temperature, humidity, oxygen consumption, etc.).To solve the key problem is how to in the actual process of logistics distribution based on the distribution characteristics of the agricultural products, design and efficient logistics distribution dynamic path planning algorithm, for producers and business operators to provide comprehensive transportation of low cost, low consumption goods, convenient agricultural products logistics distribution solutions, enhance the competitiveness of the products in the target market.3.2 Business maximum similarity matching algorithmThe depth of the rapid spread of the Internet and search engine development, the number of sellers buyers make e-commerce platform to soar, new "asymmetric information". For buyers to identify the seller's information effectively has become very difficult, resulting in platform is very difficult to find suitable suppliers; For sellers, is very difficult to get buyers information also, the promotion of the problems of high cost and low profit margins. How to improve the purity of information, enhancing business matching efficiency becomes the e-commerce platform must face the problem. Through the analysis of Web data mining, user access patterns, user records of consumption and user survey data, the analysis of the mining knowledge extraction system developed a smart website. Its key technology is automatic information acquisition technology, data mining technology, the automatic indexing technology, full-text retrieval technology and statistical techniques, etc. For example, the use of collaborative Filtering (Collaborative Filtering), according to the statisticalanalysis of a customer before buying behavior and purchase behavior from similar customers buying behavior to speculate that the customer pay attention to the goods and is related to its business scope of business opportunities, etc.3.3 Based on the concept of search engineResearch oriented knowledge element mining of massive unstructured resources and its semantic relation rapidly detect algorithms; In the semantic environment, intelligent service involves a large number of dynamic distribution in the network information resources, in order to improve the efficiency of semantic environment knowledge mining and found that the quality of knowledge, to these information resources are extracted and synthesis of the available knowledge organization, to guarantee the knowledge and effectiveness. Research under the guidance of ontology for mass and space-time distribution of unstructured information resources of multi-level knowledge mining technology, realization of metadata, the relationship between concepts and their semantic knowledge element mining components in different levels; Research knowledge learning sample complexity and computational complexity of the algorithm, establish a formal representation of the learning process, including reasonable constraint are knowledge semantic relation learning framework, achieve comprehensive knowledge, the knowledge element compound raise the level of knowledge processing, solve for Knowledge complex problems.3.4 The human-computer interaction technologyIn the human-computer Interaction technology (the Human - Computer Interaction Techniques) refers to the dialogue with the Computer technology. It includes machine through the output or display device provide people with information, people through the input device to the machine input information, etc. The human-computer interaction technology is one of the important content of computer user interface design. It and cognitive science, ergonomics, psychology, and other areas of the discipline are closely linked, and the farmer's cultural level is generally low. So the convenient, quick, the human-computer interaction interfaces and operation method of humanization, personalization and easy to use interactive equipment, for rapid advance village, e-commerce is of great significance. Touchscreen machine is a special service terminal and public service facilities of rural grassroots, because it possesses the characteristics of convenient operation, the use of free and brought to the attention of the government departments at all levels. Therefore, research on a touch screen support dialogue and remote update service platform, has a practical significance.4 Concrete measures4.1 Construct consumer shopping concept change of business operation modeConsumers shopping habits are traditional "to see, touch, listening to the sounds and taste" .Despite the multimedia electronic commerce network advertising effect, but can't replace agricultural character and the universal attraction for consumers. Only consumer shopping idea changes, adapt to the direction of the network development, B2C e-commerce of agricultural products can be developed on a large scale.4.2 Strengthen the construction of enterprise network and improve the quality of website informationEnterprises should open channels of information with the help of the Internet technology, further to do a good job of online marketing. In addition, studies have shown that for a shopping experience for the peasants agriculture website information quality, seriously affect their purchase intention. Information is most widely network buyers mentioned one of the aspects in need of improvement, and at present most of the agricultural B2C website information quality is not satisfactory.4.3 Set up online security system and payment systemA key problem of online trading is safety, including safety communications, safety confirmation and pays three aspects. There are a lot of information on the Internet have illicit close sex, online transactions need to confirm the identity to ensure that electronic non-repudiation after signing the agreement. Set up online payment system is the development of network marketing is an important content, the research shows that 52% of users think the biggest issue online shopping is not safe and convenient payment, development and security of online payment system is very necessary.4.4 Simplify the purchasing process of agricultural productsThe current electronic payment means, is network consumers mention most the place that needs to be improved, the second is to simplify the shopping process and after-sales service. In fact, there are some farmers consumers are ready to the purchase of agricultural products through the agricultural website, but in the process of clearing, settlement steps too complicated or be asked to fill out the web site of personal information too much and give up halfway. This part of the farmers is the most likely potential customers, part of which is the most worth fighting for customers. Payment platform by using simple shopping program, simplify the buying process of agricultural products, at the same time improve the quality of after-sales service, make farmers customers feel in agricultural website to buy agricultural products is both simple and trust, thus for enterprise to create more opportunities of electronic trading.译文B2C 农村电子商务网站Gleeson M1 引言B2C是电子商务的一种模式，也就是通常说的直接面向消费者销售产品和服务商业零售模式。
2018届研究生硕士学位论文分类号：学校代码： 10269密级：学号： 51151201023East China Normal University硕士学位论文MASTER’S DISSERTATION论文题目：基于多源信息表示学习的知识图谱补全算法研究院系：计算机科学与软件工程学院专业：计算机科学与技术研究方向：知识图谱指导教师：顾君忠教授学位申请人：鲍开放2018年4月Dissertation for Master’s Degree in 2018Classification Code: University Code: 10269 Confidence Level: Student ID: 51151201023EAST CHINA NORMAL UNIVERSITYTitle: Research on Algorithms of Knowledge Graph Completion Based onMulti-source Information RepresentationLearningDepartment: School of Computer Science and Software Engineering Major: Computer Science and Technology Research Area: Knowledge Graph Supervisor: Prof. Junzhong Gu Mater Candidate: Kaifang BaoApril , 2018华东师范大学硕士学位毕业论文基于多源信息表示学习的知识图谱补全算法研究鲍开放硕士学位论文答辩委员会成员名单姓名职称单位备注华东师范大学计算机科学与软件答辩主席林欣研究员工程学院计算机科学技术系华东师范大学计算机科学与软件王峰副研究员工程学院计算机科学技术系华东师范大学计算机科学与软件杨静副教授工程学院计算机科学技术系基于多源信息表示学习的知识图谱补全算法研究摘要知识图谱中含有大量形如（实体1，关系，实体2）这样的三元组，为诸多人工智能应用提供了可被计算机理解的结构化数据。
融合多尺度通道注意力的开放词汇语义分割模型SAN作者：武玲张虹来源：《现代信息科技》2024年第03期收稿日期：2023-11-29基金项目：太原师范学院研究生教育教学改革研究课题（SYYJSJG-2154）DOI：10.19850/ki.2096-4706.2024.03.035摘要：随着视觉语言模型的发展，开放词汇方法在识别带注释的标签空间之外的类别方面具有广泛应用。
相比于弱监督和零样本方法，开放词汇方法被证明更加通用和有效。
文章研究的目标是改进面向开放词汇分割的轻量化模型SAN，即引入基于多尺度通道注意力的特征融合机制AFF来改进该模型，并改进原始SAN结构中的双分支特征融合方法。
然后在多个语义分割基准上评估了该改进算法，结果显示在几乎不改变参数量的情况下，模型表现有所提升。
这一改进方案有助于简化未来开放词汇语义分割的研究。
关键词：开放词汇；语义分割；SAN；CLIP；多尺度通道注意力中图分类号：TP391.4；TP18 文献标识码：A 文章编号：2096-4706（2024）03-0164-06An Open Vocabulary Semantic Segmentation Model SAN Integrating Multi Scale Channel AttentionWU Ling， ZHANG Hong（Taiyuan Normal University， Jinzhong 030619， China）Abstract： With the development of visual language models， open vocabulary methods have been widely used in identifying categories outside the annotated label. Compared with the weakly supervised and zero sample method， the open vocabulary method is proved to be more versatile and effective. The goal of this study is to improve the lightweight model SAN for open vocabularysegmentation， which introduces a feature fusion mechanism AFF based on multi scale channel attention to improve the model， and improve the dual branch feature fusion method in the original SAN structure. Then， the improved algorithm is evaluated based on multiple semantic segmentation benchmarks， and the results show that the model performance has certain improvement with almost no change in the number of parameters. This improvement plan will help simplify future research on open vocabulary semantic segmentation.Keywords： open vocabulary; semantic segmentation; SAN; CLIP; multi scale channel attention 0 引言識别和分割任何类别的视觉元素是图像语义分割的追求。
英文折行算法The English Line Breaking Algorithm is a crucial component in the field of text rendering and layout. It is responsible for determining the optimal way to break lines of text within a given container or width, ensuring that the text is displayed in a visually appealing and easy-to-read manner. This algorithm plays a vital role in various applications, from word processors and web browsers to mobile apps and e-readers.The primary goal of the English Line Breaking Algorithm is to distribute the text evenly across multiple lines, while minimizing the occurrence of unsightly gaps or irregularities in the layout. This is particularly important in languages like English, where the presence of variable-width characters, such as punctuation marks and different letter combinations, can make it challenging to achieve a consistent and aesthetically pleasing line break.One of the key factors that the algorithm must consider is the concept of "word wrapping." This refers to the process of breaking a line of text at the end of a word, rather than in the middle of a word,to maintain the integrity of the text and improve readability. The algorithm must also take into account the presence of hyphenation, which can be used to split long words across multiple lines, further enhancing the overall layout.Another crucial aspect of the English Line Breaking Algorithm is its ability to handle different text alignment options, such as left-aligned, right-aligned, centered, and justified. Each of these alignment styles requires a unique approach to line breaking, as the algorithm must ensure that the text is distributed evenly and consistently across the available space.In the case of justified text alignment, the algorithm must also consider the use of inter-word spacing adjustments to achieve a uniform right-hand margin. This can be a delicate balance, as excessive spacing can lead to unnatural-looking text, while insufficient spacing can result in unsightly gaps between words.The English Line Breaking Algorithm is also responsible for handling special cases, such as the presence of inline images, mathematical equations, or other non-textual elements within the content. These elements can introduce additional complexities, as the algorithm must ensure that they are properly integrated into the overall layout without compromising the readability of the surrounding text.One of the key challenges in implementing an effective English Line Breaking Algorithm is the need to strike a balance between efficiency and accuracy. The algorithm must be able to process text quickly and efficiently, particularly in real-time applications like web browsers or mobile apps, where users expect immediate responsiveness. At the same time, the algorithm must produce high-quality results that maintain the integrity and aesthetics of the text layout.To achieve this balance, algorithm designers often employ a combination of heuristic approaches and advanced optimization techniques. These may include the use of dynamic programming, greedy algorithms, or even machine learning models to predict the optimal line breaks based on the characteristics of the text and the desired layout constraints.Furthermore, the English Line Breaking Algorithm must be able to handle a wide range of languages and scripts, as well as different writing systems and typographic conventions. This requires the algorithm to be highly adaptable and configurable, allowing it to be tailored to the specific needs of different applications and user interfaces.In recent years, the development of the English Line Breaking Algorithm has become increasingly important as the demand for high-quality text rendering and layout has grown across a widerange of digital platforms and devices. From the ubiquitous web browsers to the increasingly sophisticated e-book readers and mobile apps, the need for efficient and visually appealing text layout has become a critical factor in the user experience.As technology continues to evolve, the English Line Breaking Algorithm is likely to become even more sophisticated, incorporating advanced techniques and leveraging the power of emerging technologies like artificial intelligence and machine learning. These advancements may enable the algorithm to make even more intelligent decisions about line breaks, taking into account factors such as the semantic and contextual relationships between words, the visual aesthetics of the layout, and the specific preferences and needs of individual users.In conclusion, the English Line Breaking Algorithm is a fundamental component of modern text rendering and layout systems. Its ability to efficiently and effectively distribute text across multiple lines, while maintaining the integrity and readability of the content, is essential for creating high-quality user experiences across a wide range of digital platforms and applications. As the demand for advanced text layout solutions continues to grow, the development and refinement of the English Line Breaking Algorithm will remain a critical area of focus for researchers, developers, and designers alike.。
doi:10.3969/j.issn.1003-3114.2024.02.018引用格式:王浩博,吴伟,周福辉,等.智能反射面增强的多无人机辅助语义通信资源优化[J].无线电通信技术,2024,50(2): 366-372.[WANG Haobo,WU Wei,ZHOU Fuhui,et al.Optimization of Resource Allocation for Intelligent Reflecting Surface-enhanced Multi-UAV Assisted Semantic Communication[J].Radio Communications Technology,2024,50(2):366-372.]智能反射面增强的多无人机辅助语义通信资源优化王浩博1,吴㊀伟1,2∗,周福辉2,胡㊀冰3,田㊀峰1(1.南京邮电大学通信与信息工程学院,江苏南京210003;2.南京航空航天大学电子信息工程学院,江苏南京211106;3.南京邮电大学现代邮政学院,江苏南京210003)摘㊀要:无人机(Unmanned Aerial Vehicle,UAV)为无线通信系统提供了具有高成本效益的解决方案㊂进一步地,提出了一种新颖的智能反射面(Intelligent Reflecting Surface,IRS)增强多UAV语义通信系统㊂该系统包括配备IRS的UAV㊁移动边缘计算(Mobile Edge Computing,MEC)服务器和具有数据收集与局部语义特征提取功能的UAV㊂通过IRS 优化信号反射显著改善了UAV与MEC服务器的通信质量㊂所构建的问题涉及多UAV轨迹㊁IRS反射系数和语义符号数量联合优化,以最大限度地减少传输延迟㊂为解决该非凸优化问题,本文引入了深度强化学习(Deep Reinforce Learn-ing,DRL)算法,包括对偶双深度Q网络(Dueling Double Deep Q Network,D3QN)用于解决离散动作空间问题,如UAV轨迹优化和语义符号数量优化;深度确定性策略梯度(Deep Deterministic Policy Gradient,DDPG)用于解决连续动作空间问题,如IRS反射系数优化,以实现高效决策㊂仿真结果表明,与各个基准方案相比,提出的智能优化方案性能均有所提升,特别是在发射功率较小的情况下,且对于功率的变化,所提出的智能优化方案展示了良好的稳定性㊂关键词:无人机网络;智能反射面;语义通信;资源分配中图分类号:TN925㊀㊀㊀文献标志码:A㊀㊀㊀开放科学(资源服务)标识码(OSID):文章编号:1003-3114(2024)02-0366-07Optimization of Resource Allocation for Intelligent ReflectingSurface-enhanced Multi-UAV Assisted Semantic CommunicationWANG Haobo1,WU Wei1,2∗,ZHOU Fuhui2,HU Bing3,TIAN Feng1(1.School of Communications and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing210003,China;2.College of Electronic and Information Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing211106,China;3.School of Modern Posts,Nanjing University of Posts and Telecommunications,Nanjing210003,China)Abstract:Unmanned Aerial Vehicles(UAV)present a cost-effective solution for wireless communication systems.This article introduces a novel Intelligent Reflecting Surface(IRS)to augment the semantic communication system among multiple UAVs.The system encompasses UAV equipped with IRS,Mobile Edge Computing(MEC)servers,and UAV featuring data collection and local semantic feature extraction functions.Optimizing signal reflection through IRS significantly enhances communication quality between drones and MEC servers.The formulated problem entails joint optimization of multiple drone trajectories,IRS reflection coefficients,and the number of semantic symbols to minimize transmission delays.To address this non-convex optimization problem,this paper introduces a Deep收稿日期:2023-12-31基金项目:国家重点研发计划(2020YFB1807602);国家自然科学基金(62271267);广东省促进经济发展专项资金(粤自然资合[2023]24号);国家自然科学基金(青年项目)(62302237)Foundation Item:National K&D Program of China(2020YFB1807602);National Natural Science Foundation of China(62271267);Key Program of Marine Economy Development Special Foundation of Department of Natural Resources of Guangdong Province(GDNRC[2023]24);National Natural Sci-ence Foundation of China(Young Scientists Fund)(62302237)ＲｅｉｎｆｏｒｃｅｍｅｎｔＬｅａｒｎｉｎｇ（ＤＲＬ）ａｌｇｏｒｉｔｈｍ．Ｓｐｅｃｉｆｉｃａｌｌｙ，ｔｈｅＤｕｅｌｉｎｇＤｏｕｂｌｅＤｅｅｐＱＮｅｔｗｏｒｋ（Ｄ３ＱＮ）ｉｓｅｍｐｌｏｙｅｄｔｏａｄｄｒｅｓｓｄｉｓｃｒｅｔｅａｃｔｉｏｎｓｐａｃｅｐｒｏｂｌｅｍｓｓｕｃｈａｓｄｒｏｎｅｔｒａｊｅｃｔｏｒｙａｎｄｓｅｍａｎｔｉｃｓｙｍｂｏｌｑｕａｎｔｉｔｙｏｐｔｉｍｉｚａｔｉｏｎ．Ａｄｄｉｔｉｏｎａｌｌｙ，ＤｅｅｐＤｅｔｅｒｍｉｎｉｓｔｉｃＰｏｌｉｃｙＧｒａ ｄｉｅｎｔ（ＤＤＰＧ）ａｌｇｏｒｉｔｈｍｉｓｕｔｉｌｉｚｅｄｔｏｓｏｌｖｅｃｏｎｔｉｎｕｏｕｓａｃｔｉｏｎｓｐａｃｅｐｒｏｂｌｅｍｓ，ｓｕｃｈａｓＩＲＳｒｅｆｌｅｃｔｉｏｎｃｏｅｆｆｉｃｉｅｎｔｏｐｔｉｍｉｚａｔｉｏｎ，ｅｎａｂｌｉｎｇｅｆｆｉｃｉｅｎｔｄｅｃｉｓｉｏｎ ｍａｋｉｎｇ．Ｓｉｍｕｌａｔｉｏｎｒｅｓｕｌｔｓｄｅｍｏｎｓｔｒａｔｅｔｈａｔｔｈｅｐｒｏｐｏｓｅｄｉｎｔｅｌｌｉｇｅｎｔｏｐｔｉｍｉｚａｔｉｏｎｓｃｈｅｍｅｏｕｔｐｅｒｆｏｒｍｓｖａｒｉｏｕｓｂｅｎｃｈｍａｒｋｓｃｈｅｍｅｓ，ｐａｒｔｉｃｕｌａｒｌｙｉｎｓｃｅｎａｒｉｏｓｗｉｔｈｌｏｗｔｒａｎｓｍｉｓｓｉｏｎｐｏｗｅｒ．Ｆｕｒｔｈｅｒｍｏｒｅ，ｔｈｅｉｎｔｅｌｌｉｇｅｎｔｏｐｔｉｍｉｚａｔｉｏｎｓｃｈｅｍｅｐｒｏｐｏｓｅｄｉｎｔｈｉｓｐａｐｅｒｅｘｈｉｂｉｔｓｒｏｂｕｓｔｓｔａｂｉｌｉｔｙｉｎｒｅｓｐｏｎｓｅｔｏｐｏｗｅｒｃｈａｎｇｅｓ．Ｋｅｙｗｏｒｄｓ：ＵＡＶｎｅｔｗｏｒｋ；ＩＲＳ；ｓｅｍａｎｔｉｃｃｏｍｍｕｎｉｃａｔｉｏｎ；ｒｅｓｏｕｒｃｅａｌｌｏｃａｔｉｏｎ０ 引言当前技术飞速发展的背景下，无人机（ＵｎｍａｎｎｅｄＡｅｒｉａｌＶｅｈｉｃｌｅ，ＵＡＶ）已经成为无线通信系统中一种重要的技术［１］。
基于词共现矩阵的项目关键词词库和关键词语义网络作者：王庆陈泽亚郭静陈晰王晶华来源：《计算机应用》2015年第06期摘要：针对专业领域中科技项目的关键词提取和项目词库建立的问题，提出了一种基于语义关系、利用共现矩阵建立项目关键词词库的方法。
该方法在传统的基于共现矩阵提取关键词研究的基础上，综合考虑了关键词在文章中的位置、词性以及逆向文件频率（IDF）等因素，对传统算法进行改进。
另外，给出一种利用共现矩阵建立关键词关联网络，并通过计算与语义基向量相似度识别热点关键词的方法。
使用882篇电力项目数据进行仿真实验，实验结果表明改进后的方法能够有效对科技项目进行关键词提取，建立关键词关联网络，并在准确率、召回率以及平衡F分数（一般用F1measure，是同一概念吗？是同一个概念F1score）等指标上明显优于基于多特征融合的中文文本关键词提取方法。
关键词：关键词提取；共现矩阵；关键词词库；关键词语义网络；电力项目中图分类号： TP391.1 文献标志码：A英文摘要Abstract：In order to solve the problems of keyword extraction and project keyword lexicon establishment of technological projects in professional fields， an algorithm for building the lexicon based on semantic relation and cooccurrence matrix was proposed. On the basis of conventional keyword extraction research based on cooccurrence matrix， the algorithm considered several advanced factors such as the location， property and Inverse Document Frequency （IDF） index of the keywords to improve the traditional approach. Meanwhile， a method was given for the establishment of keyword semantic network using cooccurrence matrix and hot keyword identification through computing the similarity with semantic base vector. At last， 882 project experiment documents in power field were used to perform the simulation. And the experimental results show that the proposed algorithm can effectively extract the keywords for the technological projects， establish the keyword correlation network， and has better performance in precision， recall rate and F1score than the keyword extraction algorithm of Chinese text based on multifeature fusion.英文关键词Key words：keyword extraction； cooccurrence matrix； keyword lexicon； keyword semantic network； power project0 引言关键词提取是一项对文档索引、网页索引、文档分类、文本挖掘等领域非常重要的技术。
Algorithm Design Techniques and Analysis: English VersionExercise with AnswersIntroductionAlgorithms are an essential aspect of computer science. As such, students who are part of this field must master the art of algorithm design and analysis. Algorithm design refers to the process of creating algorithms that solve computational problems. Algorithm analysis, on the other hand, focuses on evaluating the resources required to execute those algorithms. This includes computational time and memory consumption.This document provides students with helpful algorithm design and analysis exercises. The exercises are in the formof questions with step-by-step solutions. The document is suitable for students who have completed the English versionof the Algorithm Design Techniques and Analysis textbook. The exercises cover various algorithm design techniques, such as divide-and-conquer, dynamic programming, and greedy approaches.InstructionEach exercise comes with a question and its solution. Read the question carefully and try to find a solution withoutlooking at the answer first. If you get stuck, look at the solution. Lastly, try the exercise agn without referring to the answer.Exercise 1: Divide and ConquerQuestion:Given an array of integers, find the maximum possible sum of a contiguous subarray.Example:Input: [-2, -3, 4, -1, -2, 1, 5, -3]Output: 7 (the contiguous subarray [4, -1, -2, 1, 5]) Solution:def max_subarray_sum(arr):if len(arr) ==1:return arr[0]mid =len(arr) //2left_arr = arr[:mid]right_arr = arr[mid:]max_left_sum = max_subarray_sum(left_arr)max_right_sum = max_subarray_sum(right_arr)max_left_border_sum =0left_border_sum =0for i in range(mid-1, -1, -1):left_border_sum += arr[i]max_left_border_sum =max(max_left_border_sum, left_b order_sum)max_right_border_sum =0right_border_sum =0for i in range(mid, len(arr)):right_border_sum += arr[i]max_right_border_sum =max(max_right_border_sum, righ t_border_sum)return max(max_left_sum, max_right_sum, max_left_border_s um+max_right_border_sum)Exercise 2: Dynamic ProgrammingQuestion:Given a list of lengths of steel rods and a corresponding list of prices, determine the maximum revenue you can get by cutting these rods into smaller pieces and selling them. Assume the cost of each cut is 0.Lengths: [1, 2, 3, 4, 5, 6, 7, 8]Prices: [1, 5, 8, 9, 10, 17, 17, 20]If the rod length is 4, the maximum revenue is 10.Solution:def max_revenue(lengths, prices, n):if n ==0:return0max_val =float('-inf')for i in range(n):max_val =max(max_val, prices[i] + max_revenue(length s, prices, n-i-1))return max_valExercise 3: Greedy AlgorithmQuestion:Given a set of jobs with start times and end times, find the maximum number of non-overlapping jobs that can be scheduled.Start times: [1, 3, 0, 5, 8, 5]End times: [2, 4, 6, 7, 9, 9]Output: 4Solution:def maximum_jobs(start_times, end_times):job_list =sorted(zip(end_times, start_times))count =0end_time =float('-inf')for e, s in job_list:if s >= end_time:count +=1end_time = ereturn countConclusionThe exercises presented in this document provide a practical way to master essential algorithm design and analysis techniques. Solving the problems without looking at the answers will expose students to the type of problems they might encounter in real life. The document’s solutionsprovide step-by-step instructions to ensure that students can approach the problems with confidence.。
opennlp 关联规则OpenNLP（Natural Language Processing）是一个开源的自然语言处理工具包，提供了一系列用于处理文本的算法和模型。
其中之一就是关联规则算法，它在文本挖掘和信息提取中起到重要的作用。
关联规则是一种用于发现数据中的频繁项集之间的关联关系的方法。
在文本处理中，关联规则可以帮助我们发现文本中的词语之间的关联关系，从而更好地理解文本内容和抽取有用的信息。
关联规则算法的核心思想是基于频繁项集的概念。
频繁项集是指在数据集中经常同时出现的一组项的集合。
通过计算项集的支持度和置信度，可以找到频繁项集之间的关联规则。
在文本处理中，可以将文本中的词语看作项集的项。
通过分析文本数据，可以计算每个词语的支持度和置信度，从而找到词语之间的关联规则。
这些关联规则可以帮助我们发现文本中的潜在关系，例如词语的共现关系、语义关系等。
例如，我们可以使用关联规则算法来分析一篇新闻报道的文本内容。
首先，我们需要对文本进行分词，将文本划分为一系列的词语。
然后，我们可以计算每个词语的支持度和置信度，从而找到频繁项集和关联规则。
通过分析关联规则，我们可以得到一些有用的信息。
例如，我们可能发现在一篇关于体育的报道中，词语“篮球”和“比赛”经常同时出现，从而可以推断出这篇报道是关于篮球比赛的。
又或者我们可能发现在一篇关于金融的报道中，词语“股票”和“涨跌”经常同时出现，从而可以推断出这篇报道是关于股票市场的。
除了文本挖掘和信息提取，关联规则算法还可以应用于其他领域，例如市场营销和推荐系统。
在市场营销中，可以使用关联规则算法分析顾客购买历史数据，从而发现产品之间的关联关系，进而制定针对性的推广策略。
在推荐系统中，可以使用关联规则算法分析用户的行为数据，从而推荐用户可能感兴趣的产品或服务。
OpenNLP提供了丰富的功能和工具来支持关联规则算法的实现。
它提供了用于文本分词、词性标注、句法分析等任务的模型和工具，这些任务都是关联规则算法的重要组成部分。
第３７卷第７期 计算机应用与软件Ｖｏｌ ３７Ｎｏ．７２０２０年７月 ＣｏｍｐｕｔｅｒＡｐｐｌｉｃａｔｉｏｎｓａｎｄＳｏｆｔｗａｒｅＪｕｌ．２０２０基于万有引力改进的ＴｅｘｔＲａｎｋ关键词提取算法孙福权１，２ 张静静２ 刘冰玉１，２ 姜玉山１，２ 多允慧２１（东北大学秦皇岛分校 河北秦皇岛０６６００４）２（东北大学 辽宁沈阳１１０８１９）收稿日期：２０１９－０６－１５。
国家重点研发计划项目（２０１８ＹＦＢ１４０２８００）；教育部科技发展中心科研创新项目（２０１８Ａ０３０３１）；全国教育信息技术研究规划课题重点项目（１６２２２８７４）；医学影像智能计算教育部重点实验室资助项目。
孙福权，教授，主研领域：电子商务，大数据分析。
张静静，硕士生。
刘冰玉，讲师。
姜玉山，讲师。
多允慧，硕士生。
摘 要 为了提高文本关键词提取的准确性，提出基于万有引力改进的ＴｅｘｔＲａｎｋ关键词提取算法ＧｔｅｘｔＲａｎｋ。
利用万有引力模型对词语在文档中的主题影响力、词语间距离和词语间共现频率进行有效融合，构建新的Ｔｅｘｔ Ｒａｎｋ转移概率实现关键词的提取。
实验结果表明，与传统关键词提取方法相比，该算法具有显著的优越性，能够完成对关键词的相对正确的提取；同时考虑了文本中词语的语义关系和主题影响度，可以提高关键词的提取精度。
关键词 关键词 主题影响度 词向量 ＴｅｘｔＲａｎｋ 万有引力中图分类号 ＴＰ３ 文献标志码 Ａ ＤＯＩ：１０．３９６９／ｊ．ｉｓｓｎ．１０００ ３８６ｘ．２０２０．０７．０３６ＡＮＩＭＰＲＯＶＥＤＴＥＸＴＲＡＮＫＫＥＹＷＯＲＤＥＸＴＲＡＣＴＩＯＮＡＬＧＯＲＩＴＨＭＢＡＳＥＤＯＮＧＲＡＶＩＴＹＳｕｎＦｕｑｕａｎ１，２ ＺｈａｎｇＪｉｎｇｊｉｎｇ２ ＬｉｕＢｉｎｇｙｕ１，２ ＪｉａｎｇＹｕｓｈａｎ１，２ ＤｕｏＹｕｎｈｕｉ２１（ＮｏｔｈｅａｓｔｅｒｎＵｎｉｖｅｒｓｉｔｙａｔＱｉｎｈｕａｎｇｄａｏ，Ｑｉｎｈｕａｎｇｄａｏ０６６００４，Ｈｅｂｅｉ，Ｃｈｉｎａ）２（ＮｏｔｈｅａｓｔｅｒｎＵｎｉｖｅｒｓｉｔｙ，Ｓｈｅｎｙａｎｇ１１０８１９，Ｌｉａｏｎｉｎｇ，Ｃｈｉｎａ）Ａｂｓｔｒａｃｔ Ｉｎｏｒｄｅｒｔｏｉｍｐｒｏｖｅｔｈｅａｃｃｕｒａｃｙｏｆｔｅｘｔｋｅｙｗｏｒｄｅｘｔｒａｃｔｉｏｎ，ｗｅｐｒｏｐｏｓｅａｎｉｍｐｒｏｖｅｄＴｅｘｔＲａｎｋｋｅｙｗｏｒｄｅｘｔｒａｃｔｉｏｎａｌｇｏｒｉｔｈｍＧｔｅｘｔＲａｎｋｂａｓｅｄｏｎｕｎｉｖｅｒｓａｌｇｒａｖｉｔａｔｉｏｎ．Ｔｈｅｕｎｉｖｅｒｓａｌｇｒａｖｉｔｙｍｏｄｅｌｗａｓｕｓｅｄｔｏｅｆｆｅｃｔｉｖｅｌｙｆｕｓｅｔｈｅｔｈｅｍｅｉｎｆｌｕｅｎｃｅ，ｔｈｅｄｉｓｔａｎｃｅｂｅｔｗｅｅｎｗｏｒｄｓａｎｄｔｈｅｃｏ ｏｃｃｕｒｒｅｎｃｅｆｒｅｑｕｅｎｃｙｏｆｗｏｒｄｓｉｎｄｏｃｕｍｅｎｔｓ，ａｎｄａｎｅｗＴｅｘｔＲａｎｋｔｒａｎｓｉｔｉｏｎｐｒｏｂａｂｉｌｉｔｙｗａｓｃｏｎｓｔｒｕｃｔｅｄｔｏｅｘｔｒａｃｔｋｅｙｗｏｒｄｓ．Ｔｈｅｅｘｐｅｒｉｍｅｎｔａｌｒｅｓｕｌｔｓｓｈｏｗｔｈａｔｃｏｍｐａｒｅｄｗｉｔｈｔｈｅｔｒａｄｉｔｉｏｎａｌｋｅｙｗｏｒｄｅｘｔｒａｃｔｉｏｎｍｅｔｈｏｄ，ｏｕｒａｌｇｏｒｉｔｈｍｈａｓｓｉｇｎｉｆｉｃａｎｔａｄｖａｎｔａｇｅｓａｎｄｃａｎｃｏｍｐｌｅｔｅｔｈｅｒｅｌａｔｉｖｅｌｙｃｏｒｒｅｃｔｅｘｔｒａｃｔｉｏｎｏｆｋｅｙｗｏｒｄｓ．Ｉｔｓｈｏｗｓｔｈａｔｔｈｅａｃｃｕｒａｃｙｏｆｋｅｙｗｏｒｄｅｘｔｒａｃｔｉｏｎｃａｎｂｅｉｍｐｒｏｖｅｄｂｙｃｏｎｓｉｄｅｒｉｎｇｂｏｔｈｔｈｅｓｅｍａｎｔｉｃｒｅｌａｔｉｏｎｓｈｉｐｏｆｗｏｒｄｓａｎｄｔｈｅｄｅｇｒｅｅｏｆｔｏｐｉｃｉｎｆｌｕｅｎｃｅ．Ｋｅｙｗｏｒｄｓ Ｋｅｙｗｏｒｄ Ｔｏｐｉｃｉｎｆｌｕｅｎｃｅ Ｗｏｒｄｖｅｃｔｏｒ ＴｅｘｔＲａｎｋ Ｕｎｉｖｅｒｓａｌｇｒａｖｉｔａｔｉｏｎ０ 引 言文本文档可以由一个或多个简单而有意义的关键词来表示，通过关键词可以了解作者的写作意图。
An Algorithm for Open Text Semantic ParsingLei Shi and Rada MihalceaDepartment of Computer ScienceUniversity of North Texasleishi@,rada@AbstractThis paper describes an algorithm for open text shal-low semantic parsing.The algorithm relies on a frame dataset(FrameNet)and a semantic network (WordNet),to identify semantic relations between words in open text,as well as shallow semantic fea-tures associated with concepts in the text.Parsing semantic structures allows semantic units and con-stituents to be accessed and processed in a more meaningful way than syntactic parsing,moving the automation of understanding natural language text to a higher level.1IntroductionThe goal of the semantic parser is to analyze the semantic structure of a natural language sentence. Similar in spirit with the syntactic parser–whose goal is to parse a valid natural language sentence into a parse tree indicating how the sentence can be syntactically decomposed into smaller syntactic constituents–the purpose of the semantic parser is to analyze the structure of sentence meaning.Sen-tence meaning is composed by entities and interac-tions between entities,where entities are assigned semantic roles,and can be further modified by other modifiers.The meaning of a sentence is decom-posed into smaller semantic units connected by var-ious semantic relations by the principle of compo-sitionality,and the parser represents the semantic structure–including semantic units as well as se-mantic relations,connecting them into a formal for-mat.In this paper,we describe the main components of the semantic parser,and illustrate the basic pro-cedures involved in parsing semantically open text. We believe that such structures,reflecting various levels of semantic interpretation of the text,can be used to improve the quality of text processing appli-cations,by taking into account the meaning of text. The paper is organized as follows.Wefirst de-scribe the semantic structure of English sentences, as the basis for semantic parsing.We then intro-duce the knowledge bases utilized by the parser,and show how we use this knowledge in the process of semantic parsing.Next,we describe the parsing algorithm and elaborate on each of the three main steps involved in the process of semantic parsing: (1)syntactic and shallow semantic analysis,(2)se-mantic role assignment,and(3)application of de-fault rules.Finally,we illustrate the parsing process with several examples,and show how the semantic parsing algorithm can be integrated into other lan-guage processing systems.2Semantic StructureSemantics is the denotation of a string of symbols, either a sentence or a word.Similar to a syn-tactic parser,which shows how a larger string is formed by smaller strings from a formal point of view,the semantic parser shows how the denotation of a larger string–sentence,is formed by deno-tations of smaller strings–words.Syntactic rela-tions can be described using a set of rules about how a sentence string is formally generated using word strings.Instead,semantic relations between seman-tic constituents depend on our understanding of the world,which is across languages and syntax.We can model the sentence semantics as describ-ing entities and interactions between entities.Enti-ties can represent physical objects,as well as time, places,or ideas,and are usually formally realized as nouns or noun phrases.Interactions,usually real-ized as verbs,describe relationships or interactions between participating entities.Note that a partic-ipant can also be an interaction,which can be re-garded as an entity nominalized from an interaction. We assign semantic roles to participants,and their semantic relations are identified by the case frame introduced by their interaction.In a sentence,par-ticipants and interactions can be further modified by various modifiers,including descriptive modi-fiers that describe attributes such as drive slowly, restrictive modifiers that enforce a general denota-tion to become more specific such as musical in-strument,referential modifiers that indicate partic-ular instances such as the pizza I ordered.Other semantic relations can also be identified,such as coreference,complement,and others.Based on the principle of compositionality,the sentence semantic structure is recursive,similar to a tree.The semantic parser analyzes shallow-level se-mantics,which is derived directly from linguis-tic knowledge,such as rules about semantic role assignment,lexical semantic knowledge,and syntactic-semantic mappings,without taking into account any context or common sense knowledge. The parser can be used as an intermediate semantic processing tool before higher levels of text under-standing.3Knowledge Bases for Semantic Parsing One major problem faced by many natural language understanding applications that rely on syntactic analysis of text,is the fact that similar syntactic pat-terns may introduce different semantic interpreta-tions.Likewise,similar meanings can be syntac-tically realized in many different ways.The seman-tic parser attempts to solve this problem,and pro-duces a syntax-independent representation of sen-tence meaning,so that semantic constituents can be accessed and processed in a more meaningful and flexible way,avoiding the sometimes rigid interpre-tations produced by a syntactic analyzer.For in-stance,the sentences I boil water and water boils contain a similar relation between water and boil, even though they have different syntactic structures. To deal with the large number of cases where the same syntactic relation introduces different seman-tic relations,we need knowledge about how to map syntax to semantics.To this end,we use two main types of knowledge–about words,and about rela-tions between words.Thefirst type of knowledge is drawn from WordNet–a large lexical database with rich information about words and concepts. We refer to this as word-level knowledge.The lat-ter is derived from FrameNet–a resource that con-tains information about different situations,called frames,in which semantic relations are syntacti-cally realized in natural language sentences.We call this sentence-level knowledge.In addition to these two lexical knowledge bases,the parser also utilizes a set of manually defined rules,which en-code mappings from syntactic structures to seman-tic relations,and which are also used to handle those structures not explicitly addressed by FrameNet or WordNet.In this section,we describe the type of infor-mation extracted from these knowledge bases,and show how this information is encoded in a format accessible to the semantic parser.3.1Frame Identification and Semantic RoleAssignmentFrameNet(Johnson et al.,2002)provides the knowledge needed to identify case frames and se-mantic roles.FrameNet is based on the theory of frame semantics,and defines a sentence level on-tology.In frame semantics,a frame corresponds to an interaction and its participants,both of which denote a scenario,in which participants play some kind of roles.A frame has a name,and we use this name to identify the semantic relation that groups together the semantic roles.In FrameNet,nouns, verbs and adjectives can be used to identify frames. Each annotated sentence in FrameNet exempli-fies a possible syntactic realization for the seman-tic roles associated with a frame for a given target word.By extracting the syntactic features and cor-responding semantic roles from all annotated sen-tences in the FrameNet corpus,we are able to auto-matically build a large set of rules that encode the possible syntactic realizations of semantic frames. In our implementation,we use only verbs as target words for frame identification.Currently, FrameNet defines about1700verbs attached to230 different frames.To extend the parser coverage to a larger subset of English verbs,we are using Verb-Net(Kipper et al.,2000),which allows us to handle a significantly larger set of English verbs. VerbNet is a verb lexicon compatible with Word-Net,but with explicitly stated syntactic and se-mantic information using Levin’s verb classification (Levin,1993).The fundamental assumption is that the syntactic frames of a verb as an argument-taking element are a direct reflection of the underlying se-mantics.Therefore verbs in the same VerbNet class usually share common FrameNet frames,and have the same syntactic behavior.Hence,rules extracted from FrameNet for a given verb can be easily ex-tended to verbs in the same VerbNet class.To en-sure a correct outcome,we have manually validated the FrameNet-VerbNet mapping,and corrected the few discrepancies that were observed between Verb-Net classes and FrameNet frames.3.1.1Rules Learned from FrameNet FrameNet data“is meant to be lexicographically rel-evant,not statistically representative”(Johnson et al.,2002),and therefore we are using FrameNet as a starting point to derive rules for a rule-based se-mantic parser.To build the rules,we are extracting several syn-tactic features.Some are explicitly encoded in FrameNet,such as the grammatical function(GF)and phrase type(PT)features.In addition,other syntactic features are extracted from the sentence context.One such feature is the relative position(RP)to the target word.Sometimes the same syntactic constituent may play different se-mantic roles according to its position with respect to the target word.For instance the sentences:I pay you.and You pay me.have different roles assigned to the same lexical unit you based on the relative position with respect to the target word pay. Another feature is the voice of the sentence.Con-sider these examples:I paid Mary500dollars.and I was paid by Mary500dollars.In these two sen-tences,I has the same values for the features GF,PT and RP,but it plays completely different roles in the same frame because of the difference of voice.If the phrase type is prepositional phrase(PP),we also record the actual preposition that precedes the phrase.Consider these examples:I was paid for my work.and I was paid by Mary.The prepositional phrases in these examples have the same values for the features GF,PT,and RP,but different preposi-tions differentiate the roles they should play.After we extract all these syntactic features,the semantic role is appended to the rule,which creates a mapping from syntactic features to semantic roles. Feature sets are arranged in a list,the order of which is identical to that in the sentence.The or-der of sets within the list is important,as illustrated by the following example:“I give the boy a ball.”Here,the boy and a ball have the same features as described above,but since the boy occurs be-fore a ball,then the boy plays the role of recipi-ent.Altogether,the rule for a possible realization of a frame exemplified by a tagged sentence is an ordered sequence of syntactic features with their se-mantic roles.For instance,Table1lists the syntactic and se-mantic features extracted from FrameNet for the sentence I had chased Selden over the moor.had chased over the moorExt objPT Target PPbefore afterV oice activeRole PathTable1:Example sentence with syntactic and se-mantic featuresThe corresponding formalized rule for this sen-tence is:[active,[ext,np,before,theme],[obj,np, after,goal],[comp,pp,after,over,path]]In FrameNet,there are multiple annotated sen-tences for each frame to demonstrate multiple pos-sible syntactic realizations.All possible realizations of a frame are collected and stored in a list for that frame,which also includes the target word,its syn-tactic category,and the name of the frame.All the frames defined in FrameNet are transformed into this format,so that they can be easily handled by the rule-based semantic parser.3.2Word Level KnowledgeWordNet(Miller,1995)is the resource used to iden-tify shallow semantic features that can be attached to lexical units.For instance,attribute relations, adjective/adverb classifications,and others,are se-mantic features extracted from WordNet and stored together with the words,so that they can be directly used in the parsing process.All words are uniformly defined,regardless of their class.Features are assigned to each word,in-cluding syntactic and shallow semantic features,in-dicating the functions played by the word.Syntactic features are used by the feature-augmented syntac-tic analyzer to identify grammatical errors and pro-duce syntactic information for semantic role assign-ment.Semantic features encode lexical semantic in-formation extracted from WordNet that is used to determine semantic relations between words in var-ious situations.Features can be arbitrarily defined,as long as there are rules to handle them.The features we define encode information about the syntactic category of a word,number and countability for nouns,transitivity and form for verbs,type,degree, and attribute for adjectives and adverbs,and others. Table2lists the main features used for content words.FeatureNounssingular/pluralCountabilityVerbstransitive/intransitive/double transitive Formparticiple/past participleTypearbitraryDegreeAdverbsdescriptive/restrictive/referentialAttributebase/comparative/superlativeTable2:Features for content wordsFor example,for the word dog,the entry in thelexicon is defined as:lex(dog,W):-W=[parse:dog,cat:noun,num:singular,count:countable].Here,the category(cat)is defined as noun,the number(num)is singular,and we also record the countability(count)1.For adjectives,the value of the attribute feature is also stored,which is provided by the attribute re-lation in WordNet.This relation links a descriptive adjective to the attribute(noun)it modifies,such as slow→speed.For example,for the adjective slow, the entry in the lexicon is defined as:lex(slow,W):-W=[parse:slow,cat:adj,attr:speed,degree:base,type:descriptive].Here,the category(cat)is defined as adjective, the type is descriptive,degree is base form.We also record the attr feature,which is derived from the at-tribute relation in WordNet,and links a descriptive adjective to the attribute(noun)it modifies,such as slow→speed.We are also exploiting the transitional relations from adverbs to adjectives and to nouns.We noticed that some descriptive adverbs have correspondence to descriptive adjectives,which in turn are linked to nouns by the attribute ing these transi-tional links,we derive relations like:slowly→slow →speed.A typical descriptive adverb is defined as follows:lex(slowly,W):-W=[parse:slowly,cat:adv, attr:speed,degree:base,type:descriptive].In addition to incorporating semantic information from WordNet into the lexicon,this word level on-tology is also used to derive default rules,as dis-cussed later.3.3Hand-coded KnowledgeThe FrameNet database encodes various syntac-tic realizations only for semantic roles within a frame.Syntax-semantics mappings other than se-mantic roles are manually encoded as rules inte-grated in the syntactic-semantic analyzer.The an-alyzer determines the syntactic structure of the sen-tence,and once a particular syntactic constituent is identified,its corresponding mapping rules are immediately applied.The syntactic constituent istity E belongs to the ontological category C if thenoun E is a child node of C in the WordNet seman-tic hierarchy of nouns.For example,if we definethe ontological category for the role“instrument”asinstrumentality,then all hyponyms of instrumental-ity can play this role,while other nouns like“boy”,which are not part of the instrumentality categorywill be rejected.Selectional restrictions are definedusing a Disjunctive Normal Form(DNF)in the fol-lowing format:[Onto(ID,P),Onto(ID,P),...],[Onto(ID,P),...],...Here,“Onto”is a noun and ID is its Word-Net sense,which uniquely identifies Onto as anode in the semantic network.“P”can be setto p(positive)or n(negative),denoting if a nounshould belong to the given category or not.Forexample,[person(1,n),object(1,p)],[substance(1,p)]means that the noun should belong to object(sense#1)but not person(sense#1)2,or it should belongto substance(sense#1).This information is addedto the rules derived from FrameNet,and thereforeafter this step,a complete FrameNet rule entry is:[Voice,[GF,PT,SelectionalRestriction,Role],...].4Semantic ParsingThe general procedure of semantic parsing consistsof three main steps3:(1)The syntactic-semanticanalyzer analyzes the syntactic structure,and useshand-coded rules as well as lexical semantic knowl-edge to identify some semantic relations betweenconstituents.It also prepares syntactic features forsemantic role assignment in the next step.(2)Therole assigner uses rules extracted from FrameNet,and assigns semantic roles for identified partici-pants,based on their syntactic features as producedin thefirst step.(3)For those constituents not exem-plified in FrameNet,we apply default rules to decidetheir default meaning.4.1Feature Augmented Syntactic-SemanticAnalyzerThe analyzer is implemented as a bottom-up chartparsing algorithm based on features.We includerules of syntax-semantics mappings in the unifica-tion based formalism.The parser analyzes syntac-tic relations and immediately applies correspondingmapping rules to obtain semantic relations when a4Since military is not a descriptive adjective,it cannot bemodified by very and predicative use is forbidden.5Adverbs are treated as modifiers.ontological categories.For example,“book”is the ontological category of the phrase“the interesting book”and“on the book”.“person”is the ontolog-ical category we manually define for the pronoun “he”.We have also defined several special onto-logical categories that are not in WordNet such as any,which can be matched to any selectional re-striction,nonperson,which means everything ex-cept person,and others.Note that this matching procedure also plays the role of a word sense dis-ambiguation tool,by selecting only those categories that match the current frame constituents.After this step,target words and syntactic constituents can be assigned with the corresponding case frame and semantic roles during the second step of semantic parsing.4.1.3Identify some semantic relationsSome semantic relations can be identified in this phase.These semantic relations include word level semantic relations,and some semantic relations that have direct syntactic correspondence by using syntax-semantics mapping rules.This phase can also identify the function of the sentence such as assertion,query,yn-query,command etc,based on syntactic patterns of the sentence.The output of the analyzer is an intermediate for-mat suitable for the semantic parser,which contains syntactic features and identified semantic relations. For example,the output for the sentence“He kicked the old dog.”is:[assertion,[[tag,ext,np,person,[[entity,[he],reference(third)],[modification(attribute),quantity(single)],[modification(attribute),gender(male)]]], [target,v,kick,active,[kick]],[modification(attribute),time(past)], [tag,obj,np,dog,[[modification(reference),reference(the)],[modification(attribute),age(old)], [target,n,dog,[dog]]]]]]4.2Semantic Role AssignmentIn the process of semantic role assignment,wefirst start by identifying all possible frames,according to the target word.Next,a matching algorithm is used tofind the most likely match among all rules of these frames,to identify the correct frame(or frames if several are possible),and assign semantic roles.In a sentence describing an interaction,we select the verb as the target word,which triggers the sen-tence level frame and uses the FrameNet rules of that target word for matching.If the verb is not defined in FrameNet and VerbNet,we use Word-Net synonymy relation to check if any of its syn-onyms is defined in FrameNet or VerbNet.If such synonyms exist,their rules are applied to the tar-get word.This approach is based on the idea in-troduced by Levin that“what enables a speaker to determine the behavior of a verb is its meaning”(Levin,1993).Synonymous verbs always intro-duce the same semantic frame and usually have the same syntactic behavior.To minimize information in the verb lexicon,non-frequently used verbs usu-ally inherit a subset of the syntactic behavior of their frequently used synonyms.Since VerbNet has defined a framework of syntactic-semantic behav-ior for these frequently used verbs,the behavior of other related verbs can be quite accurately predicted by using WordNet synonymy ing this approach,we achieve a coverage of more than3000 verbal lexical units.The matching algorithm relies on a scoring scheme to evaluate the similarity between two se-quences of features.The matching starts from the first constituent of the sentence.It looks through the list of entries in the rule and when a match is found,it moves to the next constituent looking for a new match.A match involves match of syntactic features,as well as match of selectional restrictions. An exact match means that both syntactic features and selectional restrictions are matched,which in-crements the score of matching by3.We apply selectional restriction by looking up the WordNet noun hierarchies.If the node of the ontological cat-egory is within the areas that the selectional restric-tion describes,this is regarded as a match.When applying selectional restrictions,due to polysemy of the ontological entries,we try all possible senses, starting from the most frequently used sense accord-ing to WordNet,until one sense meets the selec-tional restriction.If the syntactic features match ex-actly,but none of the possible word senses meet the selectional restrictions,this is regarded as a partial match,which increments the score by2.Partial matching is also possible,for a relaxed application of selectional restriction.This enables anaphora and metaphor resolution,in which the constituents have either unknown ontological cate-gory,or inherit features from other ontological cat-egories(by applying high level knowledge such as personification).The number of subjects and ob-jects as well as their relative positions should be strictly obeyed,since any variations may result in significant differences for semantic role labeling. Prepositional phrases are free in their location be-cause the preposition is already a unique identi-fier.Finally,after all constituents have found their match,if there are still remaining entries in the rule,the total score is decreased by1.This is a penalty paid by partial matches,since additional constituents may indicate different semantic role la-beling,which may change the interpretation of the entire sentence.A polysemous verb may belong to multiple frames,and a frame pertaining to a given target word may have multiple possible syntactic realiza-tions,exemplified by different sentences in the cor-pus.We try to match the syntactic features in the in-termediate format with all the rules of all the frames available for the target word,and compare their matching scores.The rule with the highest score is selected,and used for semantic role assignment. Through this scoring scheme,the matching algo-rithm tries to maximize the utilization of syntactic and semantic information available in the sentence, to correctly identify case frames and semantic roles.4.2.1Walk-Through ExampleAssume the following two rules,triggered for the target word break:1:[active,[ext,np,[[person(1,p)]],agent], [obj,np,[[object(1,p)]],theme],[comp,pp,with,[[instrumentality(3,p)]],instrument]]2:[[ext,np,[[instrumentality(3,p)]],instrument], [obj,np,[[person(1,n),object(1,p)]],theme]]3:[[ext,np,[[person(1,n),object(1,p)]],theme]] And the sentences:A:I break the window with a hammerB:The hammer breaks the windowC:The window breaks on the wallThe features identified by the analyzer are:A’:[[ext,np,active,person],[obj,np,active,window],[comp,pp,active,with,hammer]]B’:[[ext,np,active,hammer],[obj,np,active,window]]C’:[[ext,np,active,window],[comp,pp,on,wall]]Using the matching/scoring algorithm,the score for matching A’to rule1is determined as9since there are3exact matches,and to rule2as5since there is an exact match for“the window”but a par-tial match for“I”.Hence,the matching algorithm selects rule1,and the semantic role for“I”is agent. Similarly,when we match B’to rule1,we obtain a score of4,since there is an exact match for“the window”,a partial match for“the hammer”,and rule1has an additional entry for a prepositional phrase,which decrements the score by1.It makes a larger score of6for matching with rule2.There-fore,for the second case,the role assigned to“the hammer”is instrument.Rule3is not applied to the first two sentences since they have additional ob-jects;similarly,rule1and2cannot be applied to sentence C for the same reason.Thefirst constituent in Cfinds an exact match in rule3with a total score of3,and hence“the window”is assigned the correct role theme.The prepositional phrase“on the wall”, for which no entry for labeling a role is found in rule 3,will be handled by default rules(see Section4.3). Based on the principle of compositionality,mod-ifiers and constituents assigned semantic roles can describe interactions,so the semantic role assign-ment is performed recursively,until all roles within frames triggered by all target words are assigned.4.3Applying Default RulesWe always assign semantic roles to subjects and ob-jects6,but only some prepositional phrases can in-troduce semantic roles,as defined in the FrameNet case frames.Other prepositional phrases function as modifiers;in order to handle these constituents, and allow for a complete semantic interpretation of the sentence,we have defined a set of default rules that are applied as the last step of the semantic pars-ing process.For example,FrameNet defines a role for the prepositional phrase on him in“I depend on him”but not for on the street in“I walk on the street”,because it does not play a role,but it is a modifier describing a location.Since the role for the prepositional phrase beginning with on is not de-fined for the target word walk in FrameNet,we ap-ply the default rule that“on something”modifies the location attribute of the interaction walk.Note that we include selectional restriction in the default rule since constituents with the same syntactic features such as“on Tuesday”and“on the table”may have obviously different semantic interpretations.An ex-ample of a default rule is shown below,indicating that the interpretation of a prepositional phrase fol-lowed by a time period(where time6Where a subject and object are usually realized by noun phrases,noun clauses,or infinitive forms.tic parsing process.5Parser Output and EvaluationWe illustrate here the output of the semantic parser on a natural language sentence,and show the corresponding semantic structure and tree7.For example,for the sentence I like to eat Mexican food because it is spicy,the semantic parser produces the following encoding of sentence type,frames,se-mantic constituents and roles,and various attributes and modifiers:T=assertionP=[[experiencer,[[entity,[i],reference(first)], [modification(attribute),quantity(single)]]], [interaction(experiencer_subj),[love]], [modification(attribute),time(present)], [content,[[interaction(ingestion),[eat]],[ingestibles,[entity,[food]][[modification(restriction),[mexican]], ]]]],[reason,[[agent,[[entity,[it],reference(third)],[modification(attribute),quantity(single)]]], [description,[modification(attribute),time(present)]],[modification(attribute),taste_property(spicy)]]]]The corresponding parse tree is shown in Figure1.Figure1:Semantic parse tree(am=attributive modifier, rm=referential modifier,sm=restrictive modifier)We have conducted evaluations of the semantic role assignment algorithm on350sentences ran-domly selected from FrameNet.The test sentences were removed from the FrameNet corpus,and the rules-extraction procedure described earlier in the paper was invoked on this reduced corpus.All test sentences were then semantically parsed,and full semantic annotations were produced for each sen-tence.Notice that the evaluation is conducted only。
