基于Ontology的数据库自然语言查询接口的研究

提出了一种基于Ontology的关系数据库自然语言查询接口的系统模型及设计框架.采用WordNet作为基本数据库并在WordNet之上定义领域词库,可以提高语法分析的识别率;同时利用Ontlogly知识表达能力存储关系数据库概念模型,并对概论模型的内容进行扩充;另外对Ontology和WordNet的同义词集进行关联,可以提高语义的识别率.用户的输入查询语句通过语法分析、语义分析生成中间表达式语言DRS,然后通过模板技术转换成SQL,通过DBMS执行SQL并返回结果.实验证明,这种方案不但实用可行,而且通过逐步完善Ontology知识库的定义,可以大大提高查询的命中率;另外通过WordNet和Ontology定义领域词库和领域知识,提高了系统的可移植性.最后,所提供的方法可以很容易地移植到其他领域.     

SWSNL: Semantic Web Search Using Natural Language

As modern search engines are approaching the ability to deal with queries expressed in natural language, full support of natural language interfaces seems to be the next step in the development of future systems. The vision is that of users being able to tell a computer what they would like to find, using any number of sentences and as many details as requested. In this article we describe our effort to move towards this future using currently available technology. The Semantic Web framework was chosen as the best means to achieve this goal. We present our approach to building a complete Semantic Web Search Using Natural Language (SWSNL) system. We cover the complete process which includes preprocessing, semantic analysis, semantic interpretation, and executing a SPARQL query to retrieve the results. We perform an end-to-end evaluation on a domain dealing with accommodation options. The domain data come from an existing accommodation portal and we use a corpus of queries obtained by a Facebook campaign. In our paper we work with written texts in the Czech language. In addition to that, the Natural Language Understanding (NLU) module is evaluated on another domain (public transportation) and language (English). We expect that our findings will be valuable for the research community as they are strongly related to issues found in real-world scenarios. We struggled with inconsistencies in the actual Web data, with the performance of the Semantic Web engines on a decently sized knowledge base, and others.     

Semantic interpretation of a database query language

In this paper, we will discuss a system that semantically interprets a formal database accessing language and generates natural language from this interpretation. In the past, the major way of communication between a user and a database was by means of a formal language. One such language is the SQL query language. Even though constructed as a user friendly language, SQL exemplifies the same difficulties for users as do other formal languages, namely a fairly rigid syntax, the necessity of variable binding, the lack of pronouns, and in the case of erroneous queries error messages that do not provide much insight. To alleviate some of the formal language problems, yet utilize the power of the formal language, we set out to build a natural language ‘umbrella’ for the SQL user. Our goal was not to build a natural language query system, but rather to use semantic knowledge and natural language for paraphrasing the formal language (SQL) and producing error messages as a feedback mechanism. In this way we build a genuine help facility, which would not only aid the user in dealing with SQL, but also trap erroneous queries.     

Semantic and pragmatic processing in FIDO: A flexible interface for data-base operations

This article deals with a flexible natural language interface to access data stored in a relational data base. This interface may prove of great value to the less sophisticated user.The FIDO system (Flexible Interface for Database Operations) is presented; it accepts queries issued in natural language (Italian) and translates them into relational algebra operations. FIDO is composed of a parser (not described in the paper), a two-level semantic network, which (among other things) expresses the correspondence between the natural language terms and the conceptual database objects, and a translator/optimizer, which translates the conceptual query into its logical equivalent (i.e. into a query expressed in terms of stored relations and their attributes). The article describes the main characteristics of the semantic network and addresses, in greater detail, the problem of query translation and optimization.The flexibility of FIDO is due to the complete independence of the semantic knowledge source from the logical schema of the data base. In fact, the logical schema can be designed on the basis of considerations not related to the overall structure of FIDO (e.g. the presence of particular types of applications that have to be implemented in a particularly efficient way). In principle, the (relational) data base could be preexistent with respect to the adoption of FIDO, in that the data structures used by the translator/optimizer and described in this paper are able to describe the correspondence between the conceptual model of the domain and different logical schemas.     

From keywords to semantic queries—Incremental query construction on the semantic web

Constructing semantic queries is a demanding task for human users, as it requires mastering a query language as well as the schema which has been used for storing the data. In this paper, we describe QUICK, a novel system for helping users to construct semantic queries in a given domain. QUICK combines the convenience of keyword search with the expressivity of semantic queries. Users start with a keyword query and then are guided through a process of incremental refinement steps to specify the query intention. We describe the overall design of QUICK, present the core algorithms to enable efficient query construction, and finally demonstrate the effectiveness of our system through an experimental study.     

Type-Aware Question Answering over Knowledge Base with Attention-Based Tree-Structured Neural Networks

Question answering (QA) over knowledge base (KB) aims to provide a structured answer from a knowledge base to a natural language question. In this task, a key step is how to represent and understand the natural language query. In this paper, we propose to use tree-structured neural networks constructed based on the constituency tree to model natural language queries. We identify an interesting observation in the constituency tree: different constituents have their own semantic characteristics and might be suitable to solve different subtasks in a QA system. Based on this point, we incorporate the type information as an auxiliary supervision signal to improve the QA performance. We call our approach type-aware QA. We jointly characterize both the answer and its answer type in a unified neural network model with the attention mechanism. Instead of simply using the root representation, we represent the query by combining the representations of different constituents using task-specific attention weights. Extensive experiments on public datasets have demonstrated the effectiveness of our proposed model. More specially, the learned attention weights are quite useful in understanding the query. The produced representations for intermediate nodes can be used for analyzing the effectiveness of components in a QA system.     

数据集成中XML数据查询语义重写

查询重写是数据库研究的一个基本问题，它和查询优化，数据仓库，数据集成，语义缓存等数据库问题密切相关，为提高集成系统的查询效率，系统选择提交频率较高的XML查询物化为中间层视图，用户提交查询后，系统尽可能利用中间视图层中视图，而不是访问数据源来回答查询，这个问题实际可以归结为半结构化查询重写问题，考虑到中间视图层空间的有限性，已有视图应当尽可能回答更多的查询，传统查询重写方法有考虑半结构化数据之间的约束，而根据约束可以等价变换查询，从而提高中间视图层中的表达能力，提出了一种新的半结构化查询重写的方法，该方法在保证算法正确性和完备性的基础上，利用上半结构化数据中的约束，尤其是XML文件中的路径依赖，来增强中间层物化视图的表达能力，理论分析和初步原型实验证明方法的有效性。     

基于伪自然语言理解的CAI开发平台

基于伪自然语言理解,提出并实现了一个种高效率的知识获取方法,并把它用一诉开发中。首先知识工程师利用来自然语言的ＢＬ语言 写书本自然描述,然后利用知识编译系统处理ＢＬ程序以高效率地实现书本知识获取,再后领域专家在书本知识库的基本语义呆引导下利用知识求精系统对书本知识库加以少许求精,接着对领域知识库动态全局规划,把领域知识分解成一个个概念,最后通过方法生成组织成一个个课文传授予学生。     

基于自裁剪异构图的NL2SQL模型

自然语言转换为结构化查询语言（NL2SQL）是语义解析领域的重要任务,其核心为对数据库模式和自然语言问句进行联合学习。现有研究通过将整个数据库模式和自然语言问句联合编码构建异构图,使得异构图中引入大量无用信息,并且忽略了数据库模式中不同信息的重要性。为提高NL2SQL模型的逻辑与执行准确率,提出一种基于自裁剪异构图与相对位置注意力机制的NL2SQL模型（SPRELA）。采用序列到序列的框架,使用ELECTRA预训练语言模型作为骨干网络。引入专家知识,对数据库模式和自然语言问句构建初步异构图。基于自然语言问句对初步异构图进行自裁剪,并使用多头相对位置注意力机制编码自裁剪后的数据库模式与自然语言问句。利用树型解码器和预定义的SQL语法,解码生成SQL语句。在Spider数据集上的实验结果表明,SPRELA模型执行准确率达到71.1%,相比于相同参数量级别的RaSaP模型提升了1.1个百分点,能够更好地将数据库模式与自然语言问句对齐,从而理解自然语言查询中的语义信息。     

Using semantic components to search for domain-specific documents: An evaluation from the system perspective and the user perspective

We seek to leverage an expert user's knowledge about how information is organized in a domain and how information is presented in typical documents within a particular domain-specific collection, to effectively and efficiently meet the expert's targeted information needs. We have developed the semantic components model to describe important semantic content within documents. The semantic components model for a given collection (based on a general understanding of the type of information needs expected) consists of a set of document classes, where each class has an associated set of semantic components. Each semantic component instance consists of segments of text about a particular aspect of the main topic of the document and may not correspond to structural elements in the document. The semantic components model represents document content in a manner that is complementary to full text and keyword indexing. This paper describes how the semantic components model can be used to improve an information retrieval system. We present experimental evidence from a large interactive searching study that compared the use of semantic components in a system with full text and keyword indexing, where we extended the query language to allow users to search using semantic components, to a base system that did not have semantic components. We evaluate the systems from a system perspective, where semantic components were shown to improve document ranking for precision-oriented searches, and from a user perspective. We also evaluate the systems from a session-based perspective, evaluating not only the results of individual queries but also the results of multiple queries during a single interactive query session.     

Making the knowledge base systems more efficient: a method todetect inconsistent queries

The processing cost of queries with an empty answer, both in the database and knowledge base context, is usually high. One purpose of semantic query optimization methods in the database context is to use semantic knowledge to detect such types of queries. Although semantic query optimization is well known in the database context, this is not the case for knowledge base systems (KBSs). This paper presents a method that allows the detection of queries with an empty answer using only semantic information expressed in the knowledge base definition. The method can be applied in the context of KBSs that provide some of the following features: structuring mechanisms, assertional knowledge, temporal information, and handling of inequality expressions     

OWL-QL—a language for deductive query answering on the Semantic Web

This paper discusses the issues involved in designing a query language for the Semantic Web and presents the OWL query language (OWL-QL) as a candidate standard language and protocol for query–answering dialogues among Semantic Web computational agents using knowledge represented in the W3Cs ontology web language (OWL). OWL-QL is a formal language and precisely specifies the semantic relationships among a query, a query answer, and the knowledge base(s) used to produce the answer. Unlike standard database and Web query languages, OWL-QL supports query–answering dialogues in which the answering agent may use automated reasoning methods to derive answers to queries, as well as dialogues in which the knowledge to be used in answering a query may be in multiple knowledge bases on the Semantic Web, and/or where those knowledge bases are not specified by the querying agent. In this setting, the set of answers to a query may be of unpredictable size and may require an unpredictable amount of time to compute.     

面向对象的语义关联数据模型查询语言在C语言中的嵌入

在这篇论文里,我们重点讨论在C语言里嵌入面向对象的查询语言OSDL所遇到的矛盾及处理方法,完整地提出了在C中支持使用OSDL的宿主语言接口OSDL-C。文中提出的宿主语言接口设计思想,对于如何在过程性语言里嵌入面向对象及语义数据模型的查询语言具有一定普遍意义。     

Parallel natural language processing on a semantic network array processor

This paper presents a parallel natural language processing system implemented on a marker-passing parallel AI computer, the Semantic Network Array Processor (SNAP). Our system uses a memory-based parsing approach in which parsing is viewed as a memory search process. Linguistic information is stored as phrasal patterns in a semantic network knowledge base distributed over the memory of the parallel computer. Parsing is performed by recognizing and linking phrasal patterns that reflect a sentence interpretation. This is achieved by propagating markers over the distributed network. We have developed a system capable of processing newswire articles from a particular domain. The paper presents the structure of the system, the memory-based parsing method used, and the performance results obtained.<>     

Word segmentation based on database semantics in NChiql

In this paper a novel word-segmentation algorithm is presented to delimit words in CHinese natural language queries in NChiql system,a Chinese natural language query interface to databases.Although there are sizalbe literatures on Chinese segmentation.,they cannot satisfy particular requirements in this system,The novel word-segmentation algorithm is based on the database semantics,namely Semantic Conceptual Model(SCM) for specific domain Knowledge,Based namely Semantic COnceptual Model(SCM) for specific domain knowledge,Based on SCM,the segmenter labels the database semantics to words directly,which eases the disambiguation and translation(from natural language to database query)in NChiql.