Search

Examines the use of Chinese language processing techniques for temporal information extraction (IE) and concept reasoning. Characteristics of time system and temporal expressions; Discussion of temporal knowledge representation; Framework for extracting temporal concepts; Proposed temporal IE model; Temporal information from Hong Kong, China, financial news reports.

Focuses on the importance of Science and Technology (S&T) text mining in extracting useful information from technical materials. Role of text mining on peer reviews and other decision-making process; Components of text mining; Definition of S&T text mining; Analysis of phrase patterns by computational linguistics.

Describes a methodology of extraction, optimization and application of sets of logical rules. Competitiveness of neural methods in providing simple and accurate sets of logical rules; Characterization of the taxonomy of the neural rule extraction algorithms; Types of logical rules; Context-dependent linguistic variables; Rule extraction algorithms; Extraction of rules; Methodology of extraction of crisp/fuzzy logical rules.

This article argues that overt multiple wh-fronting in languages like Bulgarian consists of moving a single wh-cluster to [Spec, CP]. The formation of wh-clusters is motivated by the assumption that wh-elements can act as landing sites for wh-movement due to morphological properties of wh-words. I further argue that languages such as Japanese constitute covert instances of this process of wh-cluster formation, accounting for intricate constraints on multiple wh-questions such as the so-called "additional-wh effect." Another central claim of the article is that despite appearances, multiple wh-questions in German equally involve the formation of wh-clusters, which are shown to consist of one visible and one or more invisible wh-elements. This analysis provides a new account for the lack of "short" and the presence of "long" superiority effects in German. [ABSTRACT FROM AUTHOR]

Recently, the prevalence of information retrieval engines has created an important application of the automatic summarization as the display of retrieval results, whereby the user can quickly and accurately judge the relevance of texts returned as a result of a query. Here, rather than producing a generic summary, the summary that reflects the user's topic of interest (information need) expressed in the query would be considered as more suitable. This type of summary is often called query-biased summary. In this paper we present a method for producing query-biased summaries using lexical chains. Lexical chains are sequences of words that are in lexical cohesion relation with each other, and tend to indicate fragments of a text that form a semantic unit. Using lexical chains would enable to produce more coherent and readable summaries than previous approaches to query-biased summarization. To evaluate the effectiveness of our method, a task-based evaluation scheme is adopted. The results from the experiments show that query-biased summaries by lexical chains outperform others in the accuracy of subjects' relevance judgments. [ABSTRACT FROM AUTHOR]

This paper describes a machine learning approach to building an efficient and accurate name spotting system. Finding names in free text is an important task in many text-based applications. Most previous approaches were based on hand-crafted modules encoding language and genre-specific knowledge. These approaches had at least two shortcomings: They required large amounts of time and expertise to develop and were not easily portable to new languages and genres. This paper describes an extensible system that automatically combines weak evidence from different, easily available sources: parts-of-speech tags, dictionaries, and surface-level syntactic information such as capitalization and punctuation. Individually, each piece of evidence is insufficient for robust name detection. However, the combination of evidence, through standard machine learning techniques, yields a system that achieves performance equivalent to the best existing hand-crafted approaches. [ABSTRACT FROM AUTHOR]

Presents a minimalist analysis of Condition on Extraction Domains (CED) effects in terms of derivational dynamics in a cyclic system. Basic CED effects; Sideward movements and cyclic access to numeration; Conclusion.

In this paper I develop an argument for a pied-piping approach to the apparent absence of island effects in Japanese, along the lines of Nishigauchi (1986, 1990). The argument (first mentioned in Watanabe (1992b), crediting Mamoru Saito) has to do with the behavior of multiple wh-phrases in situ which are in an island; such wh-phrases must all take the same scope. On a covert pied-piping approach to island effects, the ban on distinct scopes follows straightforwardly; the island must be pied-piped to a scope position by the wh-phrases inside it, establishing the scope position for all of them. I show that the ban on distinct-scope readings does exhibit several properties of islands, including additional-wh effects. I then go on to investigate briefly the nature of pied-piping, developing a theory which accounts for the fact that wh- islands cannot be pied-piped. [ABSTRACT FROM AUTHOR]

Applies the information extraction (IE) technology to scientific journal papers in molecular biology in the United States. Tasks included in an IE system; Function of the LaSIE system for IE; Support of LaSIE by the General Architecture for Text Engineering software; LaSIE application in two separate bioinformatics research projects.

As is well known, in conditionals and, more generally, in structures involving adverbs of quantification, indefinite NPs like a cat display a variable quantificational force. Within DRT this phenomenon is analyzed by assimilating indefinites to variables. Unlike other variable-like elements, however, indefinites cannot be anaphoric to something else. That is, one cannot say things like "a cat usually meows if a cat is hungry" meaning "a cat usually meows if it is hungry." This is generally explained in terms of a novelty condition: indefinites must introduce novel variables. Cheng and Huang (1996) discuss and analyze two types of Chinese conditionals in which wh- words display quantificational variability. In one type of conditional, their behavior is fully analogous to that of indefinites. In the other, they behave like indefinites in the antecedent, while in the consequent they must be interpreted as bound pronouns. Thus, in DR-theoretic terms, Chinese wh-words obey the novelty condition in the antecedent but not in the consequent of a conditional. This behavior is unexpected. The present paper addresses this issue. The main claim is that a certain version of Dynamic Semantics leads one to expect elements with exactly the properties of Chinese wh-words. In particular, Dynamic Semantics makes it possible to reverse, in a sense, the classic DR-theoretic strategy. One can view indefinites as existentially quantified terms: however, their existential force can be overridden by operators in their local environment that wipe out their existential force, as it were, and get them to act like variables. If one takes this line, the Novelty Condition becomes dispensable and the problem disappears. The behavior of Chinese wh-words is also compared to that of other elements analyzable as indefinite pronominals, such as si in Italian or one in English. [ABSTRACT FROM AUTHOR]

Provides information on a study which described techniques for stroke extraction used in the recognition of handwritten Chinese characters. How to detect feature points from skeletons; Ways to determine end and fork points; Correction of distorted skeletons; Conclusions.

Rule extraction with neural networks is a subject of increasing interest. Research in this area could benefit from the availability of a formal model of the semantics of the rules. A model of this kind would express the relationship between the application data, the neural network learning model and the extracted rules with mathematical rigor, allowing systematic analysis and modification of rule extraction approaches and the neural network architectures used. However, formal models of this kind are not in common use. This paper proposes a formal semantic model and includes an analysis of an example rule extraction architecture and some issues raised by it and other architectures. In the formal model, the semantics of a neural network is expressed through a form of model theory based upon concepts from topology, including limit points and continuous functions. A state of adaptation of the neural network in which it has learned a set of rules from training data corresponds to a continuous function between topological systems. Topological systems, the domains of inputs to the network, are a generalization of the concept of a topological space. The results of an example analysis with this model suggest a direction for improvements to the example architecture and the desirability of applying the model to other rule extraction approaches. [ABSTRACT FROM AUTHOR]

One of the reasons why pitch extraction from speech has been difficult is that pitch is nonstationary and changes over a wide range. In most of the conventional methods, it is assumed that speech remains stationary in an analysis frame of fixed width. This essentially produces an extraction error. In order to remedy this point, there have been attempts to apply the wavelet transform to the pitch extraction, where the resolution can be adjusted dynamically on the time–frequency plane [5, 6]. This paper proposes an implementation of pitch extraction based on discrete wavelet transform, which can execute the computation efficiently by a subband filter bank for pitch filtering. Since the subband filter bank contains internal down-sampling, aliasing in the pitch filtering is a problem. In the proposed method, aliasing is avoided by scaling of the input signal. A computer simulation is tried for the test signal and actual speech. The synthesized test signal includes the first three harmonic components, and the pitch frequency is increased exponentially so that the time variation is faster for higher frequencies. It is verified that the pitch can be extracted with an error rate of about ±2% for any pitch frequency. © 1999 Scripta Technica, Electron Comm Jpn Pt 3, 82(6):36–45, 1999 [ABSTRACT FROM AUTHOR]

Abstract. In Albanian a K-word can be used as an interrogative, as a polarity item (PI) and, in combination with certain particles, as a quantifier. I propose an analysis of these elements as variables in the sense of Heim (1982). In order to receive an interrogative reading, a K-word must obligatorily move to a Focus phrase projection. Overt movement is due to the presence of a (strong) Focus feature on the K-word. In the absence of such a feature, a K-word remains in situ and can only be interpreted as a PI. The set of possible binders that license PI includes the negation, question operators, conditional complementizers, modal verbs and modal particles. The properties of PIs are satisfied by covert dependency formation. This dependency does not involve abstract movement but rather a binding relation. More precisely, polarity items and their operators form a head-to-head dependency sensitive to strong and weak islands. [ABSTRACT FROM AUTHOR]

The article presents information on the use of transformational rammer theory in the language teaching field. The discussions about the use of transformational principles in the field of education is growing. Transformational grammar has revealed the extent to which languages have deep and surface structure differences, underlying regularity, and universal similarity. These discoveries have great relevance in the field of education. Materials prepared by the teachers of English as second Language are oriented almost invariably toward imparting as a final goal the ability of the student to give phonological shape to surface structures. Mastery of deep structure principles is just as important, if not more so, since it is these which govern linguistic interpretation. Teachers must try to bring awareness among the students about deep structure differences which would enable them to have control over them. This aim could be realized through the pertinent nature and organization of the textual resources.

The article examines that Enamel interproximal reduction (IPR) is another way to increase the space available to relieve crowding and considered as an alternative to extraction. Topics include considered that programmed IPR (p-IPR) should correspond to what is clinically implemented IPR to achieve the desired alignment with accurate interproximal contacts.

• We propose TOP-Rank which incorporates both topical and positional information to rank phrases. • Classification of phrases in keyphrases and non-keyphrases by identifying topical significance using similarity measures. • Ranking of keyphrases using intra-cluster and inter-cluster ranking to identify the top most keyphrase from top most cluster. • Comparison of the similarity measures for keyphrase extraction. • Improving classification of keyphrases as Processes, Materials and Tasks. Keyphrase extraction is the task of extracting the most important phrases from a document. Automatic keyphrase extraction attempts to itemize a document content as metainformation and facilitate efficient information retrieval. In this paper we propose TOP-Rank, an approach for keyphrase extraction and keyphrase classification. For keyphrase extraction, we build an approach based on the position of keyphrases in the document and expand it with topical ranking of keyphrases. In particular, keyphrase extraction technique analyzes the documents and extracts keyphrases from the document by giving a higher rank to topical phrases. After keyphrase extraction, we classify keyphrases as process, material and task. Our evaluation on diverse datasets shows that TOP-Rank achieves F1-score of 0.73 for keyphrase classification improving upon state-of-the-art methods by a huge margin. [ABSTRACT FROM AUTHOR]

Chapter 6 of the book "Foundations and Trends in Databases: Information Extraction," Vol. 1, is presented. It explains that many applications depend on the automatic extraction of structure from unstructured data for better means of querying, organizing, and analyzing data. It also discusses the concluding remarks about the topics discussed in this book.

The article highlights the workshop on Computational and Computer-Assisted Terminology on May 25, 2005 in Lisbon, Portugal. The major themes discussed in the workshop were term extraction, semantic relation extraction, and terminology and knowledge organization and management. It also reflected the increasing development of terminological tools in a variety of languages.

A correction to the article "Ergativity and the Complexity of Extraction: A View From Mayan" by Lauren Eby Clemens et al. that was published in a 2014 issue is presented.

An abstract of the article "Scope, Prosody, and Pitch Accent: The Prosodic Marking of Wh-Scope in Two Varieties of Japanese and South Kyeongsang Korean," by Hyun Kyung Hwang is presented.

This article presents a study, which further examines the comprehension of wh-movement structures by agrammatic aphasic individuals using eyetracking. It also examines the role that syntactic complexity plays in the on-line comprehension of these structures, comparing the comprehension of more simple non-canonical wh-questions and complex object clefts. Results show that means accuracy of yes-no and wh-question comprehension was high for both participant groups, with yes/no comprehension at 85% for aphasic participants and 95% for controls and wh-question comprehension at 100% correct for controls and 92.5% correct for agrammatics. It demonstrates a tight link between on-line performance in eyetracking tasks and off-line sentence comprehension, even in disordered populations. This suggests that eyetracking can be useful as an on-line measure of linguistic deficits and recovery.

A correction to the article "Automatic extraction and categorization of Faenza Codex figurations'" by Sarig Sela and Roni Y. Granot in the xlii/4 issue of 2014.

The article focuses on the extraction of an embeddded content of a document. It states that documents can be embedded inside other documents, and identifying, extracting, and separately processing embedded content can be beneficial. It further discusses that deciding the unit of retrieval is the major concern for the extraction of embedded documents.

An abstract of the article "The Importance of Being a Complement: CED Effects Revisited," by Johannes Jurka is presented.

The article presents different methods in the automatic glossary extraction. It is noted that Atsushi Fujii and Tetsuya Ishikawa presented a method that extracts fragments of Web pages using patterns used to describe terms. The method of Youngja Park and colleagues extracts glossary items on the basis of a pipeline architecture. Meanwhile, the text-mining method of Judith Klavans and Smaranda Muresan extracts definitions embedded in online texts based on pattern matching at the lexical level and guided by cue phrases.

The article presents a view of a case study that compared complement selection in British and American English. Texts from 18th and 19th century fiction literature were studied with the present day British and American language styles used in newspaper texts. The results of the comparison show change in variants through the time period. The author finds that extraction may be the probable cause for the selection of complements. It is suggested that extraction of the direct object of the subordinate clause favors the more frequent use of the present complement in the British English when compared with American English.