领域知识文档的语义检索方法研究

语义检索是解决信息检索中准确度、人性化要求的一个非常有潜力的方法。通过对知识文档进行主题词标注,然后建立从词元→主题词→知识文档的二级索引结构;对用户的检索,进行查询词到主题词的转化,计算语义相似度,按照语义相似度算法进行排序文档。目前基于知识文档的语义检索系统已经在某集团公司进行部署和应用,取得了前5项结果命中用户总查询90%的效果,说明这种方法是语义检索的一种有效途径。     

A Fuzzy-Related Thesaurus for Query Refinement

Query refinement is essential for information retrieval. In this study, a fuzzy-related thesaurus based query refinement mechanism is proposed. This thesaurus can be dynamically generated during the retrieval process for a document collection that is classified by an unsupervised neural network, the self-organising map. In contrast with general relational thesaurus, the fuzzy-related thesaurus is more effective and efficient. The relationships between the terms are based on the classification of a document collection, and thus, the generated thesaurus naturally has more power to enhance retrieval quality. The recognition of the relationships can be done automatically without human involvement, which significantly reduces the cost associated with the construction of the thesaurus. An evaluation on the query refinement mechanism based on the fuzzy-related thesaurus has conducted and the preliminary result is promising. A significant improvement on retrieval performance was observed when a fuzzy-related thesaurus was used for query refinement for a software document collection.     

Thesaurus-based 3D Object Retrieval with Part-in-Whole Matching

Research in content-based 3D retrieval has already started, and several approaches have been proposed which use in different manner a similarity assessment to match the shape of the query against the shape of the objects in the database. However, the success of these solutions are far from the success obtained by their textual counterparts. A major drawback of most existing 3D retrieval solutions is their inability to support partial queries, that is, a query which does not need to be formulated by specifying a whole query shape, but just a part of it, for example a detail of its overall shape, just like documents are retrieved by specifying words and not whole texts. Recently, researchers have focused their investigation on 3D retrieval which is solved by partial shape matching. However, at the extent of our knowledge, there is still no 3D search engine that provides an indexing of the 3D models based on all the interesting subparts of the models. In this paper we present a novel approach to 3D shape retrieval that uses a collection-aware shape decomposition combined with a shape thesaurus and inverted indexes to describe and retrieve 3D models using part-in-whole matching. The proposed method clusters similar segments obtained trough a multilevel decomposition of models, constructing from such partition the shape thesaurus. Then, to retrieve a model containing a sub-part similar to a given query, instead of looking on a large set of subparts or executing partial matching between the query and all models in the collection, we just perform a fast global matching between the query and the few entries in the thesaurus. With this technique we overcame the time complexity problems associated with partial queries in large collections.     

A SKOS-based multilingual thesaurus of geological time scale for interoperability of online geological maps

The usefulness of online geological maps is hindered by linguistic barriers. Multilingual geoscience thesauri alleviate linguistic barriers of geological maps. However, the benefits of multilingual geoscience thesauri for online geological maps are less studied. In this regard, we developed a multilingual thesaurus of geological time scale (GTS) to alleviate linguistic barriers of GTS records among online geological maps. We extended the Simple Knowledge Organization System (SKOS) model to represent the ordinal hierarchical structure of GTS terms. We collected GTS terms in seven languages and encoded them into a thesaurus by using the extended SKOS model. We implemented methods of characteristic-oriented term retrieval in JavaScript programs for accessing Web Map Services (WMS), recognizing GTS terms, and making translations. With the developed thesaurus and programs, we set up a pilot system to test recognitions and translations of GTS terms in online geological maps. Results of this pilot system proved the accuracy of the developed thesaurus and the functionality of the developed programs. Therefore, with proper deployments, SKOS-based multilingual geoscience thesauri can be functional for alleviating linguistic barriers among online geological maps and, thus, improving their interoperability.     

图像语义标注中的叙词查询方法*

为了在图像语义标注领域能更好地反映标注之间的关系,通过对已标注图像的标注进行分析来建立标 注之间的关系,并在此基础上将叙词查询的概念引入到图像语义标注中并提出了基于叙词查询的图像语义标注 方法,把语义标注问题统一在叙词查询与图像的语义关系相结合在统一的框架下,最后通过在Ｃｏｒｅｌ图像数据库中的验证表明,所提出的方法是有效的并且标注率得到了明显的提高。     

基于PMI-IR的联想词表构造方法研究

通过对大规模查询日志进行挖掘分析进而提高检索的准确率一直是信息检索领域的热点问题。文章提出一种基于PMI-IR（逐点互信息方法）的联想词表构造方法。该方法利用序列模式挖掘算法扫描大规模用户查询日志,获取共现频次超过某一阈值的词组合,进行聚类获取候选同义词集,然后依次计算词wordA与每个候选词的相似度,选择相似度高于某一阈值的词作为词wordA的联想词集,最后形成联想词表。实验表明,借助该方法得到的联想词表进行扩展查询提高了检索的准确率。     

基于叙词表的领域知识图谱初始种子集自动生成算法

随着认知计算的飞速发展,通用知识图谱的自动构建取得了极大的进步,但在垂直领域由于缺乏本体等语义信息,导致进展缓慢。叙词表广泛分布于各个专业领域且蕴藏着丰富的语义信息,如能对这些语义信息进行合理的提取和利用,必然能在一定程度上帮助领域知识图谱的自动构建。该文提出两个假设,利用假设可以从叙词表内部结构中提取实体类型和关系类型,进而设计了一种基于叙词表的领域知识图谱初始种子集自动生成算法。最后,以地质领域和林业领域的叙词表作为实验对象,采用Bootstrapping算法,利用由叙词表自动生成的初始种子集进行抽取工作,通过对抽取到的结果进行分析,结果表明利用叙词表得到的初始种子集可以取得同人工设计种子比较接近的效果。此外,所提模型具有通用性,为叙词表在构建领域知识图谱中的应用提供了一种新的思路。     

Semantics analysis through elementary meanings

Abstract. Thesaurus is a collection of words classified according to some relatedness measures among them. In this paper, we lay the theoretical foundations of thesaurus construction through elementary meanings of words. The concept of elementary meanings has been advocated and utilized in compiling Webster's Collegiate Thesaurus. If each word is supplied with elementary meanings so that all its meanings are covered by them in a standard fashion, we can define various similarity measures for a given set of words. Here we take an axiomatic way to analyze semantic structure of word groups. Assuming an abstract semantic world, we deduce closed sets as generalized synonym sets. That is, we show that under certain natural axioms, we only need to consider closed sets as far as the semantics are concerned. We also show that the set of generalized synonyms described as a certain pair of closed sets has a lattice structure. In order to have a flexible thesaurus, we also analyze structure changes corresponding to three basic environmental changes: A new word-meaning relation is added, a new word or a new meaning is included with its word-meaning relations. Actually we give algorithms to have updated lattice structure from previous one for the three operations. Received: 5 May 1996 / 21 February 2000     

A content-search information retrieval process based on conceptual graphs

An intelligent information retrieval system is presented in this paper. In our approach, which complies with the logical view of information retrieval, queries, document contents and other knowledge are represented by expressions in a knowledge representation language based on the conceptual graphs introduced by Sowa. In order to take the intrinsic vagueness of information retrieval into account, i.e. to search documents imprecisely and incompletely represented in order to answer a vague query, different kinds of probabilistic logic are often used. The search process described in this paper uses graph transformations instead of probabilistic notions. This paper is focused on the content-based retrieval process, and the cognitive facet of information retrieval is not directly addressed. However, our approach, involving the use of a knowledge representation language for representing data and a search process based on a combinatorial implementation of van Rijsbergen’s logical uncertainty principle, also allows the representation of retrieval situations. Hence, we believe that it could be implemented at the core of an operational information retrieval system. Two applications, one dealing with academic libraries and the other concerning audiovisual documents, are briefly presented.     

A Lattice Conceptual Clustering System and Its Application to Browsing Retrieval

The theory of concept (or Galois) lattices provides a simple and formal approach to conceptual clustering. In this paper we present GALOIS, a system that automates and applies this theory. The algorithm utilized by GALOIS to build a concept lattice is incremental and efficient, each update being done in time at most quadratic in the number of objects in the lattice. Also, the algorithm may incorporate background information into the lattice, and through clustering, extend the scope of the theory. The application we present is concerned with information retrieval via browsing, for which we argue that concept lattices may represent major support structures. We describe a prototype user interface for browsing through the concept lattice of a document-term relation, possibly enriched with a thesaurus of terms. An experimental evaluation of the system performed on a medium-sized bibliographic database shows good retrieval performance and a significant improvement after the introduction of background knowledge.     

Using Web resources to construct multilingual medical thesaurus for cross-language medical information retrieval

Due to the language barrier, non-English users are unable to retrieve the most updated medical information from the U.S. authoritative medical websites, such as PubMed and MedlinePlus. However, currently, there is no any cross-language medical information retrieval (CLMIR) system that can help Chinese-speaking consumers cross the language barrier in finding useful English medical information. A few CLMIR systems utilize MeSH (Medical Subject Headings) to help overcome the language barrier. Unfortunately, the traditional Chinese version of MeSH is currently unavailable.In this paper, we employ a semi-automatic term translation method to construct a Chinese–English MeSH by exploiting abundant multilingual Web resources, including Web anchor texts and search–result pages. Through this method, we have developed a Chinese–English Mesh Compilation System to assist knowledge engineers in compiling a Chinese–English medical thesaurus with more than 19,000 entries. Furthermore, this thesaurus has been used to develop a prototypical system for cross-language medical information retrieval, MMODE, which can help consumers retrieve top-quality English medical information using Chinese terms.     

An automated indexing system utilizing semantic net expansion.

Automated subject indexing and the coordination of indexing with natural language search interfaces could provide solutions to some of the information retrieval problems facing the medical field today. This paper describes the construction of such an interface using semantic net expansion and a clinical neuroscience thesaurus, which provided a specialized vocabulary for use in both automated indexing of MEDLINE articles and an "intelligent" front-end for database searching. Though reviewed by a domain expert, the thesaurus was successfully built by nonexperts utilizing a set of rules. We report on testing thesaurus content and semantic net accuracy using a database of selected MEDLINE article abstracts.     

中文文献的层次分类方法

现有的分类系统通常忽略类别体系的层次结构,在对文献进行分类时,往往很难区分类别相近的文献属于哪一类。本文基于向量空间模型,提出根据类别体系的层次结构,自顶向下,逐层分类的方法。其目的是提高分类精度;并根据概念词典,将同义词或下位概念映射到单一的概念词上,由这些概念词构成一个规模很小的特征集,以缩小特征向量空间的维数,从而减少分类系统的计算量。此外,通过对类别层次体系的分析,压缩特征向量,从另一方面减少分类系统的计算量。