Centro de Investigación en Computación

The paper presents a method for automatic detection of "non-trivial" word combinations in the text. It is based on automatic syntactic analysis. The method shows better precision and recall than the baseline method (bigrams). It was tested on a text in Spanish. The method can be used for enrichment of very large dictionaries of word combinations.

The problem of document categorization is considered. The set of domains and the keywords specific for these domains is supposed to be selected beforehand as initial data. We apply the well-known statistical hypothesis test that considers images of documents and domains as normalized vectors. In comparison with existing methods, such approach allows to take into account a random character of initial data. The classifier is developed in the framework of Document Investigator software package.

La Elicitación de Requisitos de software es un proceso básico para garantizar la calidad del software y por lo general se realiza entre los Analistas y los Interesados en Lenguaje Natural, para obtener una especificación; dicha especificación suele estar conformada por un conjunto de diagramas (comúnmente de UML). El Procesamiento de Lenguaje Natural ha sido utilizado para la solución de problemas de Elicitación de Requisitos de software, pero aún utilizando lenguajes de corte técnico que los Interesados no dominan y por lo tanto no pueden validar adecuadamente. En este artículo se presenta UN-Lencep, una propuesta del uso de Lenguajes Controlados para especificación de Esquemas Preconceptuales, que se utilizan en la automatización del proceso de elaboración de diagramas UML. Adicionalmente, se muestra un ejemplo de la aplicación de UN-Lencep.

Particle Swarm Optimization (PSO) technique has proved its ability to deal with very complicated optimization and search problems. Several variants of the original algorithm have been proposed. This paper proposes a novel hybrid PSO -evolutionary algorithm for solving the well known geometrical place problems. Finding the geometrical place could be sometimes a hard task. In almost all situations the geometrical place consists more than one single point. The performance of the newly proposed PSO algorithm is compared with evolutionary algorithms. The main advantage of the PSO technique is its speed of convergence. Also, we propose a hybrid algorithm, combining PSO and evolutionary algorithms. The hybrid combination is able to detect the geometrical place very fast for which the evolutionary algorithms required more time and the conventional PSO approach even failed to find the real geometrical place.

The fast growth of Internet is creating a society where the demand on information storage, organization, access, and analysis services is continuously growing. This constantly increases the number of inexperienced users that need to access databases in a simple way. Together with the emergence of voice interfaces, such a situation foretells a promising future for database querying systems using natural language interfaces. We describe the architecture of a relational database querying system using a natural language (Spanish) interface, giving a brief explanation of the implementation of each of the constituent modules: lexical parser, syntax checker, and semantic analyzer.

We have previously suggested that Internet word usage statistics can help selecting a word choice variant out of a set of hypotheses. In this paper we show how Googe's wildcard operator can help either to directly obtain the specific word appropriate in a given context or to assure that the correct variant be included in the set of considered hypotheses.

The use of conceptual graphs for the representation of text contents in information retrieval is discussed. A method for measuring the similarity between two texts represented as conceptual graphs is presented. The method is based on well-known strategies of text comparison, such as Dice coefficient, with new elements introduced due to the bipartite nature of the conceptual graphs. Examples of the representation and comparison of the phrases are given. The structure of an information retrieval system using two-level document representation, traditional keywords and conceptual graphs, is presented. * The work was done under partial support of CONACyT, REDII, and SNI, Mexico.

Free access to full-text scientific papers in major digital libraries and other web repositories is limited to only their abstracts consisting of no more than several dozens of words. Current keyword-based techniques allow for clustering such type of short texts only when the data set is multi-category, e.g., some documents are devoted to sport, others to medicine, others to politics, etc. However, they fail on narrow domain-oriented libraries, e.g., those containing all documents only on physics, or all on geology, or all on computational linguistics, etc. Nevertheless, just such data sets are the most frequent and most interesting ones. We propose simple procedure to cluster abstracts, which consists in grouping keywords and using more adequate document similarity measure. We use Stein's MajorClust method for clustering both keywords and documents. We illustrate our approach on the texts from the Proceedings of a narrow-topic conference. Limitations of our approach are also discussed. Our preliminary experiments show that abstracts cannot be clustered with the same quality as full texts, though the achieved quality is adequate for many applications; accordingly, we suggest that digital libraries should provide document images of full texts of the papers (and not only abstracts) for open access via Internet, in order to help in search, classification, clustering, selection, and proper referencing of the papers. * Work done under partial support of the Government of Valencia, Mexican Government (CONACyT, SNI, CGPI, COFAA-IPN), R2D2 CICYT (TIC2003-07158-C04-03), and ICT EU-India (ALA/95/23/2003/077-054).

Malapropism is a (real-word) error in a text consisting in unintended replacement of one content word by another existing content word similar in sound but semantically incompatible with the context and thus destructing text cohesion, e.g.: they travel around the word. We present an algorithm of malapropism detection and correction based on evaluating the cohesion. As a measure of semantic compatibility of words we consider their ability to form syntactically linked and semantically admissible word combinations (collocations), e.g: travel (around the) world. With this, text cohesion at a content word is measured as the number of collocations it forms with the words in its immediate context. We detect malapropisms as words forming no collocations in the context. To test whether two words can form a collocation, we consider two types of resources: a collocation DB and an Internet search engine, e.g., Google. We illustrate the proposed method by classifying, tracing, and evaluating several English malapropisms. * Work done under partial support of Mexican Government (CONACyT, SNI), CGEPI-IPN, Mexico, and RITOS-2. We thank Prof. G. Hirst for useful discussion and criticism.

The main objective of Bolshakov and Gelbukh's new textbook in computational linguistics is to provide students in computer science with a foundation in the fundamentals of general linguistics necessary to develop applied software systems, and to enable students to make informed choices of proper models and data structures. Although Spanish-language applications are emphasized, the textbook contains examples from English, French, Portuguese, and Russian as well. This text is freely available in an electronic format. Supplementary materials, links to the relevant resources, and errata can be found on-line as well.

The problem of automatic text segmentation is subcategorized into two different problems: thematic segmentation into rather large topically selfcontained sections and splitting into paragraphs, i.e., lexico-grammatical segmentation of lower level. In this paper we consider the latter problem. We propose a method of reasonably splitting text into paragraph based on a text cohesion measure. Specifically, we propose a method of quantitative evaluation of text cohesion based on a large linguistic resource -a collocation network. At each step, our algorithm compares word occurrences in a text against a large DB of collocations and semantic links between words in the given natural language. The procedure consists in evaluation of the cohesion function, its smoothing, normalization, and comparing with a specially constructed threshold. PDF PS www.gelbukh.com Igor A. Bolshakov and A. Gelbukh. Text segmentation into paragraphs based on local text cohesion.

Conceptual graphs allow for powerful and computationally affordable representation of the semantic contents of natural language texts. We propose a method of comparison (approximate matching) of conceptual graphs. The method takes into account synonymy and subtype/supertype relationships between the concepts and relations used in the conceptual graphs, thus allowing for greater flexibility of approximate matching. The method also allows the user to choose the desirable aspect of similarity in the cases when the two graphs can be generalized in different ways. The algorithm and examples of its application are presented. The results are potentially useful in a range of tasks requiring approximate semantic or another structural matching -among them, information retrieval and text mining.

We propose a method of synonymous paraphrasing of a text based on WordNet synonymy data and Internet statistics of stable word combinations (collocations). Given a text, we look for words or expressions in it for which WordNet provides synonyms, and substitute them with such synonyms only if the latter form valid collocations with the surrounding words according to the statistics gathered from Internet. We present two important applications of such synonymous paraphrasing: (1) style-checking and correction: automatic evaluation and computer-aided improvement of writing style with regard to various aspects (increasing vs. decreasing synonymous variation, conformistic vs. individualistic selection of synonyms, etc.) and (2) steganography: hiding of additional information in the text by special selection of synonyms. A basic interactive algorithm of style improvement is outlined and an example of its application to editing of newswire text fragment in English is traced. Algorithms of style evaluation and information hiding are also proposed.

Prepositional Phrase (PP) attachment can be addressed by considering frequency counts of dependency triples seen in a non-annotated corpus. However, not all triples appear even in very big corpora. To solve this problem, several techniques have been used. We evaluate two different backoff methods, one based on WordNet and the other on a distributional (automatically created) thesaurus. We work on Spanish. The thesaurus is created using the dependency triples found in the same corpus used for counting the frequency of unambiguous triples. The training corpus used for both methods is an encyclopaedia. The method based on a distributional thesaurus has higher coverage but lower precision than the WordNet method.