Skip to main content

ANALISIS DE TEXTOS Y RECUPERACION DE INFORMACION PARA LA MINERIA DE OPINIONES: ANALISIS DE ENUNCIADOS Y EXTRACCION DE RELACIONES

TIN2010-18552-C03-02

•
Funding agency name Ministerio de Ciencia e Innovación
Funding agency acronym MICINN
Program Programa Nacional de Proyectos de Investigación Fundamental
Subprogram Subprograma de Proyectos de Investigación Fundamental no Orientada
Call Proyectos I+D
Call year 2010
State Plan 2008-2011 Plan Nacional de Investigación Científica, Desarrollo e Innovación Tecnológica
Management unit Subdirección General de Proyectos de Investigación
Beneficiary centre UNIVERSIDADE DA CORUÑA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 7
Encontrada(s) 1 página(s)

Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Contribución de congreso (ConferenceOutput)

Improving transition-based dependency parsing with buffer transitions

  • Fernández González, Daniel
  • Gómez Rodríguez, Carlos
In this paper, we show that significant improvements in the accuracy of well-known transition-based parsers can be obtained, without sacrificing efficiency, by enriching the parsers with simple transitions that act on buffer nodes. First, we show how adding a specific transition to create either a left or right arc of length one between the first two buffer nodes produces improvements in the accuracy of Nivre's arc-eager projective parser on a number of datasets from the CoNLL-X shared task. Then, we show that accuracy can also be improved by adding transitions involving the topmost stack node and the second buffer node (allowing a limited form of non-projectivity). None of these transitions has a negative impact on the computational complexity of the algorithm. Although the experiments in this paper use the arc-eager parser, the approach is generic enough to be applicable to any stack-based dependency parser., Ministerio de Ciencia e Innovación | Ref. TIN2010-18552-C03-01, Ministerio de Ciencia e Innovación | Ref. TIN2010-18552-C03-02, Xunta de Galicia
RUC. Repositorio da Universidade da Coruña
Publication Contribución de congreso (ConferenceOutput)

Supervised polarity classification of Spanish tweets based on linguistic knowledge

  • Vilares, David
  • Alonso, Miguel A.
  • Gómez-Rodríguez, Carlos
This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the 2013 ACM symposium on Document engineering (DocEng '13). Association for Computing Machinery, New York, NY, USA, 169–172. https://doi.org/10.1145/2494266.2494300., [Abstract]: We describe a system that classifies the polarity of Spanish tweets. We adopt a hybrid approach, which combines machine learning and linguistic knowledge acquired by means of NLP. We use part-of-speech tags, syntactic dependencies and semantic knowledge as features for a supervised classifier. Lexical particularities of the language used in Twitter are taken into account in a pre-processing step. Experimental results improve over those of pure machine learning approaches and confirm the practical utility of the proposal., Research reported in this paper has been partially funded by Ministerio de Economía y Competitividad and FEDER (Grant TIN2010-18552-C03-02) and by Xunta de Galicia (Grants CN2012/008, CN2012/319)., Xunta de Galicia; CN2012/008, Xunta de Galicia; CN2012/319
RUC. Repositorio da Universidade da Coruña
Publication Contribución de congreso (ConferenceOutput)

Sentiment analysis for reviews and microtexts based on lexico-syntactic knowledge

  • Vilares, David
[Abstract]: We describe two methods to perform sentiment analysis both on long and short texts written in Spanish language. We first present an unsupervised method based on dependency parsing which calculates the semantic orientation (SO) of the sentences in order to classify the polarity. We then propose a hybrid approach which uses the computed SO and lexico-syntactic knowledge as features for a supervised classifier. Experimental results show the utility of employing syntactic information to classify the polarity in both types of texts and the importance of defining mechanisms to adapt the system for a specific domain and social medium., Research reported in this paper has been partially funded by Ministerio de Economía y Competitividad and FEDER ( TIN2010-18552-C03-02) and by Xunta de Galicia (CN2012/008, CN2012/319)., Xunta de Galicia; CN2012/008, Xunta de Galicia; CN2012/319
RUC. Repositorio da Universidade da Coruña
Publication Contribución de congreso (ConferenceOutput)

LyS at TASS 2013: Analysing Spanish tweets by means of dependency parsing, semantic-oriented lexicons and psychometric word-properties, LyS en TASS 2013: Analizando tuits en castellano a través de análisis de dependencias, lexicones de opiniones y propiedades psicométricas del lenguaje

  • Vilares, David
  • Alonso, Miguel A.
  • Gómez-Rodríguez, Carlos
[Abstract]: This article describes the approach developed by our group in order to resolve the sentiment analysis at a global level, topic identification and political tendency classification tasks on Spanish tweets; proposed at the Workshop of Sentiment Analysis at sepln (tass 2013). As a preliminary step, we carry out an ad-hoc preprocessing in order to normalise the tweets. We then apply part-of-speech tagging and dependency parsing algorithms to the tweets to obtain their syntactic structure. Our proposal also employs psychological resources in order to exploit the psychometric properties of human language. The experimental results confirm the robustness of the proposal, which has achieved good performance in general, being the best-performing approach in the topic classification task., [Resumen]: Este artículo describe el enfoque utilizado por nuestro grupo para resolver las tareas de análisis global del sentimiento, identificación de tópicos y clasi- ficación de la tendencia política sobre tuits en español; propuestas en el Taller de Análisis del Sentimiento en la SEPLN (TASS 2013). Como paso previo, se realiza un preprocesado ad-hoc para normalizar los tuits. A continuación, se lleva a cabo un análisis morfológico de los tuits para luego obtener su estructura sintáctica aplicando algoritmos de análisis de dependencias. Nuestra propuesta también emplea recursos psicológicos, que permiten explotar las características psicométricas del lenguaje humano. Los resultados experimentales confirman la robustez de la propuesta, que en términos generales ha obtenido un buen rendimiento, alcanzando el primer puesto en la tarea de clasificación de tópicos., Research reported in this article has been partially funded by Ministerio de Economía y Competitividad and FEDER (Grant TIN2010-18552-C03-02) and by Xunta de Galicia (Grants CN2012/008, CN2012/319)., Xunta de Galicia; CN2012/008, Xunta de Galicia; CN2012/319
RUC. Repositorio da Universidade da Coruña
Publication Contribución de congreso (ConferenceOutput)

Identificación Automática del Idioma en Twitter: Adaptación de Identificadores del Estado del Arte al Contexto Ibérico, Automatic Language Identification in Twitter: Adapting State-of-the-Art Identifiers to the Iberian Context

  • Doval, Yerai
  • Vilares, David
  • Vilares, Jesús
[Abstract]: We describe here our partipation in TweetLID. After having studied the problem of language identification, the resources available, and designed a text conflation approach for this kind of tasks, we joined the competition with two sys- tems: the first one was based in the guesser langdetect, re-trained and adapted in order to work with conflated text; the second one was an approach based on majo- rity vote which used a set of re-trained and adapted classifiers. Results are analized both globally and at language and tweet-type levels., [Resumen]: Describimos aquí nuestra participación en el TweetLID. Tras estudiar la problemática de la identificación del idioma, los recursos disponibles y diseñar una solución para la normalización del texto en este tipo de tareas, presentamos dos sis- temas a competición: el primero basado en el clasificador langdetect, re-entrenado y adaptado para trabajar con texto normalizado; el segundo, una solución basada en la votación de clasificadores individuales igualmente re-entrenados y adaptados. Los resultados son analizados tanto globalmente como por idioma y tipo de tuit., Trabajo parcialmente financiado por el Ministeriode Economía y Competitividad y FEDER (TIN2010-18552-C03-02), Ministerio de Educación, Cultura y Deporte (Beca FPU ref. 13/01180) y Xunta de Galicia (CN2012/008)., Xunta de Galicia; CN2012/008
RUC. Repositorio da Universidade da Coruña
Publication Contribución de congreso (ConferenceOutput)

LyS: Porting a Twitter Sentiment Analysis Approach from Spanish to English

  • Vilares, David
  • Hermo, Miguel
  • Alonso, Miguel A.
  • Gómez-Rodríguez, Carlos
  • Doval, Yerai
[Abstract]: This paper proposes an approach to solve message- and phrase-level polarity classification in Twitter, derived from an existing system designed for Spanish. As a first step, an ad-hoc preprocessing is performed. We then identify lexical, psychological and semantic features in order to capture different dimensions of the human language which are helpful to detect sentiment. These features are used to feed a supervised classifier after applying an information gain filter, to discriminate irrelevant features. The system is evaluated on the SemEval 2014 task 9: Sentiment Analysis in Twitter. Our approach worked competitively both in message- and phraselevel tasks. The results confirm the robustness of the approach, which performed well on different domains involving short informal texts., Research reported in this paper has been partially funded by Ministerio de Economía y Competitividad and FEDER (Grant TIN2010-18552-C03-02) and by Xunta de Galicia (Grant CN2012/008), Xunta de Galicia; CN2012/008
RUC. Repositorio da Universidade da Coruña
Publication Contribución de congreso (ConferenceOutput)

Prototipado rápido de un sistema de normalización de tuitsuna aproximación léxica, Rapid prototyping of a Tweet Normalization System: A Lexical Approach

  • Vilares, Jesús
  • Alonso, Miguel A.
  • Vilares, David
[Resumen]: Este trabajo describe el sistema de normalización de tuits en español desarrollado por el Grupo de Lengua Y Sociedad de la Información (LYS) de la Universidade da Coruña para el Tweet-Norm 2013. Se trata de un sistema conceptualmente sencillo y flexible que emplea pocos recursos y que aborda el problema desde un punto de vista léxico., [Abstract]: This work describes the system for the normalization of tweets in Spanish designed by the Language in the Information Society (LYS) Group of the University of A Coruña for Tweet-Norm 2013. It is a conceptually simple and flexible system, which uses few resources and that faces the problem from a lexical point of view., Trabajo parcialmente subvencionado por el Minis-terio de Economía y Competitividad y FEDER (proyecto TIN2010-18552-C03-02) y por la Xunta de Galicia (ayudas CN 2012/008 y CN 2012/319)., Xunta de Galicia; CN 2012/008, Xunta de Galicia; CN 2012/319