• Publications
  • Influence
A Survey of Multilingual Event Extraction from Text
This paper focuses on language-specific event type identification methods for mono- and multilingual detection of socio-political events, and describes the systems that cover this functionality.
Testing Word Similarity: Language Independent Approach with Examples from Romance
This paper considers a set of models (formulae) of a given class and selects the best ones using training and test samples and demonstrates how to construct such formulae for a given language using an inductive method of model self-organization.
Constructing Empirical Models for Automatic Dialog Parameterization
The paper shows how to avoid difficulties when dealing with politeness, competence, satisfaction, and other similar characteristics of clients using empirical formulae based on lexical-grammatical properties of a text.
Modified Makagonov's Method for Testing Word Similarity and its Application to Constructing Word Frequency Lists
This work proposes a simple modification of the Makagonov approach for testing word similarity, based on empirical formulae comparing the number of equal and different letters in the two strings, using n-grams instead of letters.
Knowledge-poor Approach to Constructing Word Frequency Lists, with Example from Romance Languages
En this articulo se proponen dos procedimientos basados en formulas empiricas de similitud entre palabras, un simple ajuste de los parametros de las formulas permita su adecuacion a diferentes lenguajes europeos.
The paper is a limited review of publications (1995-2010) related to the problem of classification of clinical records presented in a free text form. The techniques of indexing and methods of
Elliphant : A Machine Learning Method for Identifying Subject Ellipsis and Impersonal Constructions in Spanish
Elliphant is useful as the classification of elliptic subjects as referential or non-referential can improve the accuracy of Natural Language Processing where zero anaphora resolution is necessary, inter alia, for information extraction, machine translation, automatic summarization and text categorization.
A Modified Tripartite Model for Document Representation in Internet Sociology
A modified model is proposed, where instead of document authors the authors consider textual mentions of persons and institutions as actors as actors, which proves to be more appropriate for the solution of a range of Internet Sociology tasks.
Regression Model for Politeness Estimation Trained on Examples
Automatic assessment of subjective characteristics of customers like politeness, satisfaction or competence could provide services companies with information needful for improving service quality. In