Skip to main content

TECNOLOGIAS DEL LENGUAJE DESDE UNA PERSPECTIVA VERDE: SELECCION DE MODELOS

PID2023-147129OB-C22

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprogram Subprograma Estatal de Generación de Conocimiento
Call Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Call year 2023
State Plan 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSIDAD DE VIGO

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

Structured sentiment analysis as transition-based dependency graph parsing

  • Fernández González, Daniel
Structured sentiment analysis (SSA) aims to automatically extract people’s opinions from a text in natural language and adequately represent that information in a graph structure. One of the most accurate methods for performing SSA was recently proposed and consists of approaching it as a dependency graph parsing task. Although we can find in the literature how transition-based algorithms excel in different dependency graph parsing tasks in terms of accuracy and efficiency, all proposed attempts to tackle SSA following that approach were based on graph-based models. In this article, we present the first transition-based method to address SSA as dependency graph parsing. Specifically, we design a transition system that processes the input text in a left-to-right pass, incrementally generating the graph structure containing all identified opinions. To effectively implement our final transition-based model, we resort to a Pointer Network architecture as a backbone. From an extensive evaluation, we demonstrate that our model offers the best performance to date in practically all cases among prior dependency-based methods, and surpasses recent task-specific techniques on the most challenging datasets. We additionally include an in-depth analysis and empirically prove that the average-case time complexity of our approach is quadratic in the sentence length, being more efficient than top-performing graph-based parsers., Universidade de Vigo/CISUG, Agencia Estatal de Investigación | Ref. PID2020-113230RB-C22, Agencia Estatal de Investigación | Ref. PID2023-147129OB-C22
Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

g-vamp: Improving sequence labelling frameworks for multiword expressions identification

  • Fernández Lanza, Santiago
  • Darriba Bilbao, Víctor Manuel
  • Fernández González, Daniel
Annotated corpora such as the parseme collection frequently contain Multiword Expressions (mwes) that share tokens within a sentence, meaning that a single token may belong to two or more mwes. This phenomenon is widespread across languages and poses a significant challenge for machine learning models that rely on standard sequence-labelling formulations. Token sharing increases training complexity and often leads to systematic prediction errors. As a result, most existing approaches resolve these conflicts by retaining only one of the overlapping mwes and discarding the others, which entails substantial information loss and can be particularly detrimental in low-resource settings. This paper introduces g-vamp (Generate Variants and Merge Predictions), a general framework that enables mwe identification systems to handle token sharing without discarding annotated expressions or relying on complex encodings. g-vamp operates by generating multiple variants of the training corpus in which token-sharing conflicts are eliminated in a controlled manner. A Transformer-based model is trained independently on each variant, and the resulting predictions are subsequently merged to recover mwes that involve shared tokens at inference time. We evaluate g-vamp on version 1.3 of the parseme multilingual corpus, covering 26 languages with diverse structural and typological characteristics. The results show that g-vamp consistently improves over a strong baseline in 24 languages and surpasses state-of-the-art systems in 16 languages, despite relying exclusively on a single multilingual Transformer model and no language-specific linguistic resources. These findings demonstrate that controlled corpus diversification constitutes an effective and language-agnostic strategy for addressing token sharing in mwe identification., Agencia Estatal de Investigación | Ref. PID2020-113230RB-C22, Agencia Estatal de Investigación | Ref. PID2023-147129OB-C22