Tagged Text Research Articles

Knowledge Extraction and Semantic Annotation of Text from the Encyclopedia of Life

Numerous digitization and ontological initiatives have focused on translating biological knowledge from narrative text to machine-readable formats. In this paper, we describe two workflows for knowledge extraction and semantic annotation of text data objects featured in an online biodiversity aggregator, the Encyclopedia of Life. One workflow tags text with DBpedia URIs based on keywords. Another workflow finds taxon names in text using GNRD for the purpose of building a species association network. Both workflows work well: the annotation workflow has an F1 Score of 0.941 and the association algorithm has an F1 Score of 0.885. Existing text annotators such as Terminizer and DBpedia Spotlight performed well, but require some optimization to be useful in the ecology and evolution domain. Important future work includes scaling up and improving accuracy through the use of distributional semantics.

Peer‐to‐peer distributed text classifier learning in PADMINI

AbstractPopular Internet document repositories, such as online newspapers, digital libraries, and blogs store large amount of text and image data that are frequently accessed by large number of users. Users' input through collaborative commenting or tagging can be very useful in organizing and classifying documents. Some web sites (e.g. Google Image Labeler) support a collection of tags and labels, but a large fraction of these sites do not currently support such activities. Moreover, relying upon centrally controlled web‐service providers for such support is probably not a good idea if the objective is to make the collaborative inputs publicly available. Often, business entities offering such web‐based tagging environments end up owning and monetizing the result of the collective effort. This paper takes a step toward addressing this problem—it proposes a peer‐to‐peer (P2P) system (PADMINI), powered by distributed data mining algorithms. In particular, it focuses on learning a P2P classifier from tagged text data. This paper describes the PADMINI system and the distributed text classifier learning components; text classification is posed as a linear program and an asynchronous distributed algorithm is used to solve it. It also presents extensive empirical results on text data obtained from the Hubble Space Telescope (HST) proposal abstract database. Copyright © 2012 Wiley Periodicals, Inc. Statistical Analysis and Data Mining 2012

Approach for Transforming Monolingual Text Corpus into XML Corpus

In this paper, we are presenting the approach to convert the text based monolingual corpus to Part-Of-Speech tagging using an standard tagging tool in tagged file and then convert tagged file in the XML format as per defined DTD (Document Type Definition). The tagged text document is parsed through the logic to generate the corpus in XML and also, it can be further used for Information Retrieval, Text-To-Speech conversion, Word Sense Disambiguation and also useful for preprocessing step of parsing by providing unique tag to each word which reduces the number of parses. General Terms Natural Language Processing

Exploring Collections of Tagged Text for Literary Scholarship

AbstractModern literary scholars must combine access to vast collections of text with the traditional close analysis of their field. In this paper, we discuss the design and development of tools to support this work. Based on analysis of the needs of literary scholars, we constructed a suite of visualization tools for the analysis of large collections of tagged text (i.e. text where one or more words have been annotated as belonging to a specific category). These tools unite the aspects of the scholars’ work: large scale overview tools help to identify corpus‐wide statistical patterns while fine scale analysis tools assist in finding specific details that support these observations. We designed visual tools that support and integrate these levels of analysis. The result is the first tool suite that can support the multilevel text analysis performed by scholars, combining standard visual elements with novel methods for selecting individual texts and identifying represenative passages in them.

Energy and Latency Efficient Access of Wireless XML Stream

In this article, we address the problem of delayed query processing raised by tree-based index structures in wireless broadcast environments, which increases the access time of mobile clients. We propose a novel distributed index structure and a clustering strategy for streaming XML data that enables energy and latencyefficient broadcasting of XML data. We first define the DIX node structure to implement a fully distributed index structure which contains the tag name, attributes, and text content of an element, as well as its corresponding indices. By exploiting the index information in the DIX node stream, a mobile client can access the stream with shorter latency. We also suggest a method of clustering DIX nodes in the stream, which can further enhance the performance of query processing in the mobile clients. Through extensive experiments, we demonstrate that our approach is effective for wireless broadcasting of XML data and outperforms the previous methods.

Eigennamenerkennung zwischen morphologischer Analyse und Part-of-Speech Tagging: ein automatentheoriebasierter Ansatz

AbstractPrevious rule-based approaches for Named Entity Recognition (NER) in German base NER on Part-of-Speech tagged texts. We present a new approach where NER is situated between morphological analysis and Part-of-Speech Tagging and model the NER-grammar entirely with weighted finite state transducers (WFST). We show that NER strategies like the resolution of proper noun/common noun or company-name/family-name ambiguities can be formulated as a best path function of a WFST. The frequently used second pass resolution of coreferential Named Entities can be formulated as a re-assignment of appropriate weights. A prototypical NE recognition system built on the basis of WSFT and large lexical resources was tested on a manually annotated corpus of 65,000 tokens. The results show that our system compares in recall and precision to existing rule-based approaches.

Merging structured text using temporal knowledge

Structured text is a general concept that is implicit in a variety of approaches in handling information. Syntactically, an item of structured text is a number of grammatically simple phrases together with a semantic label for each phrase. Items of structured text may be nested within larger items of structured text. Much information is potentially available as structured text including tagged text in XML, text in relational and object-oriented databases, and the output from information extraction systems in the form of instantiated templates. In a previous paper, we presented a framework for merging items of potentially inconsistent structured text [A. Hunter, Data & Knowledge Engineering 34 (2000) 305]. In this paper, we extend that framework by considering the need to use temporal knowledge. The primary aim of this paper is to specify the language and types of axioms required in this temporal knowledge.

Logical fusion rules for merging structured news reports

Structured text is a general concept that is implicit in a variety of approaches in handling information. Syntactically, an item of structured text is a number of grammatically simple phrases together with a semantic label for each phrase. Items of structured text may be nested within larger items of structured text. Much information is potentially available as structured text including tagged text in XML, text in relational and object-oriented databases, and the output from information extraction systems in the form of instantiated templates. In previous papers, we have presented a logic-based framework for merging items of potentially inconsistent structured text [Data Knowledge Eng. 34 (2000) 305–332, Data Knowledge Eng. 2002 (in press)]. In this paper, we present fusion rules as a way of implementing logic-based fusion. Fusion rules are a form of scripting language that define how structured news reports should be merged. The antecedent of a fusion rule is a call to investigate the information in the structured news reports and the background knowledge, and the consequent of a fusion rule is a formula specifying an action to be undertaken to form a merged report. It is expected that a set of fusion rules is defined for any given application. We give the syntax and mode of execution for fusion rules, and explain how the resulting actions give a merged report. We illustrate the presentation with examples of fusion rules for an application for merging weather reports.

Reasoning with inconsistency in structured text

Reasoning with inconsistency involves some compromise on classical logic. There is a range of proposals for logics (called paraconsistent logics) for reasoning with inconsistency each with pros and cons. Selecting an appropriate paraconsistent logic for an application depends upon the requirements of the application. Here we review paraconsistent logics for the potentially significant application area of technology for structured text. Structured text is a general concept that is implicit in a variety of approaches to handling information. Syntactically, an item of structured text is a number of grammatically simple phrases together with a semantic label for each phrase. Items of structured text may be nested within larger items of structured text. The semantic labels in a structured text are meant to parameterize a stereotypical situation, and so a particular item of structured text is an instance of that stereotypical situation. Much information is potentially available as structured text, including tagged text in XML, text in relational and object-oriented databases, and the output from information extraction systems in the form of instantiated templates. In this review paper, we formalize the concept of structured text, and then focus on how we can identify inconsistency in items of structured text, and reason with these inconsistencies. Then we review key approaches to paraconsistent reasoning, and discuss the application of them to reasoning with inconsistency in structured text.

Merging potentially inconsistent items of structured text

Structured text is a general concept that is implicit in a variety of approaches to handling information. Syntactically, an item of structured text is a number of grammatically simple phrases together with a semantic label for each phrase. Items of structured text may be nested within larger items of structured text. The semantic labels in a structured text are meant to parameterize a stereotypical situation, and so a particular item of structured text is an instance of that stereotypical situation. Much information is potentially available as structured text including tagged text in XML, text in relational and object-oriented databases, and the output from information extraction systems in the form of instantiated templates. In this paper, we formalize the concept of structured text, and then focus on how we can identify inconsistency in the logical representation of items of structured text. We then present a new framework for merging logical theories that can be employed to merge inconsistent items of structured text. To illustrate, we consider the problem of merging reports such as weather reports.

An Overview of Waterloo's Database Software for the <em>OED</em>

According to the Oxford English Dictionary, dictionary can be either a book dealing with the individual words of language... or a repository of knowledge, convenient for consultation. An effective dictionary database must serve both roles simultaneously; that is, it must be capable of answering precise questions about the written dictionary text as well as the language described by that text. An effective representation for the OED has been based on the recent text structuring technique known as 'descriptive markup', which introduces tags into text stream. Thus, dictionary components are explicitly identified and delimited, so that, for example, an entry is marked by ... , an etymology by ... , usage label by ... , and cited work by ... . The most visibly successful aspect of our research is embodied in the flexible and efficient search and display software. LECTOR is general-purpose browser that takes as input stream of tagged text and formats it to the screen using typography to illustrate its structure. It uses specially-designed formatting, or display-specification, language to accomplish this, through which the choice of typographical strategies is user-selectable. As complementary software component, efficient retrieval is provided by the PAT text search engine. Each entry in the search index designates 'semi-infinite' string that starts at critical point in the text (e.g. at word start) and continues uninterruptedly to the end of the text. Text regions (e.g. those representing individual dictionary components) can be specified to limit the scope of material being searched or displayed. Used together, PAT and LECTOR form powerful query facility for text databases. Examples drawn from our experiences with researchers and casual visitors illustrate the application of these tools to exploring the OED.

マルチメディア型言語データベースの構築とその応用について

Our joint research project of creating an original hypermedia corpus of spoken Japanese began in 1991 as a pilot study for error analyses in discourse. We have collected 'live' spoken data from actual conversation between experts of TJFL (Teaching Japanese as a Foreign Language) and several native and non-native speakers (or learners) of Japanese. The experiments were executed in the forms of free talking plus role plays, which were based upon an established testing format known as OPI (Oral Proficency Interview). The whole contents of OPI experimentation were first recorded by camcorders on several high precision video tapes, and then converted into digital video files and/or digital sound data files, using DTV hardware and software. So far, the accumulated data (compressed files) have amounted to more than 1GB, which include movie clips, sound files, and full texts transcribed from the original digital sound data. The process of text transcription and its link to video and audio data is still under way. Our research has also been motivated by a new concept of global network. Recently, a sharp rise of interest in communicating ideas and sharing resources via Intemet seems to be accelerating the move toward building up distributed databases, accessible to any user connected to the worldwide network, e.g. WWW, Gopher and WAIS. The sample movie data of our corpus project is now being transferred to WWW server (http://www.fit.ac.jp) along with HTML-based tagged texts and is expected to be available on the Internet.

Concepts for modeling and querying list-structured data

Traditionally, data models and query languages have provided mechanisms for dealing with sets of objects. Many database applications, however, are list oriented (i.e., deal with collections or aggregates of objects in which ordering is important). This article presents the list-structure data model which has ordering as a fundamental feature. The model is based on atomic, aggregate, and list constructors and thus provides support for tree-structured and sequential representations of data. These constructors can be intermixed and allow the modeling of variable and recursive schemes. Such schemes occur naturally in list-oriented data like tagged text, dictionaries, genealogies, etc. The notion of patterns found in traditional text and list processing applications is generalized to deal with the tree-structured representation and then incorporated in operations for searching, marking, updating, and restructuring list-structure instances. These operations form the core of a query language wherein users can succinctly and naturally formulate complex problems typically encountered in list-oriented database applications.

Collocational grammar system

A system for the grammatical annotation of natural language receives natural language text and annotates each word with a set of tags indicative of its possible grammatical or syntactic uses. An empirical probability of collocation function defined on pairs of tags is iteratively extended to a selected set of tag sequences of increasing length so as to select a most probable tag for each word of a sequence of ambiguously-tagged words. For listed pairs of commonly confused words a substitute calculation reveals erroneous use of the wrong word. For words with tags having abnormally low frequency of occurrence, a stored table of reduced probability factors corrects the calculation. Once the text words have been annotated with their most probable tags, the tagged text is parsed by a parser which successively applies phrasal, predicate and clausal analysis to build higher structures from the disambiguated tag strings. A voice/text translator including such a tag annotator resolves sound or spelling ambiguity of words by their differing tags. A database retrieval system, such as a spelling checker, includes a tag annotator to identify desired data by syntactic features.

The Myth of the Minstrel Manuscript

Whether known as jongleur, minstrel, gestour, disour, mimus, scurra, or by some other term, the professional entertainer who sings, tells jokes and stories, and declaims the deeds of great men is a ubiquitous figure in both medieval literature and modern scholarship. A large body of literature, not only heroic narrative such as the chansons de geste and the romances, but also fabliaux, political satires, and short comic monologues, has been confidently placed in the repertoire, and terms such as minstrel tag, minstrel style, and minstrel text are in common use. Although these attributions have met with increased suspicion in recent years,' no one has fully challenged the widespread assumption that there exists somewhere a body of manuscripts that once belonged to minstrels, manuscripts that would offer codicological evidence of the practice and range of narrative minstrelsy. The manuscripts in question are the small, plain, battered working texts that the minstrels are alleged to have carried with them on their travels. Per Nykrog, without obvious ironic intention, sums up the consensus perfectly: Personne n'a doute, je crois, de l'existence de 'manuels' dans lesquels les jongleurs conservaient leur repertoire.2 Certainly scholars have raised doubts about the ownership of individual manuscripts, but their doubts have been frequently overlooked or ignored. The diversity of minstrelsy compounds the problem: it is all too easy to assume, as Nykrog does, that while one's own area of expertise yields no firm examples of manuscripts, there must be plentiful examples in those of others. Although in many cases the individual manuscripts have already been the subject of