Listar GI-LYS - Congresos, conferencias, etc. por título
Mostrando ítems 45-64 de 71
-
On the Challenges of Fully Incremental Neural Dependency Parsing
(Association for Computational Linguistics, 2023-11)[Absctract]: Since the popularization of BiLSTMs and Transformer-based bidirectional encoders, state-of-the-art syntactic parsers have lacked incrementality, requiring access to the whole sentence and deviating from ... -
On the Logistical Difficulties and Findings of Jopara Sentiment Analysis
(Association for Computational Linguistics, 2021-06)[Abstract] This paper addresses the problem of sentiment analysis for Jopara, a code-switching language between Guarani and Spanish. We first collect a corpus of Guarani-dominant tweets and discuss on the difficulties of ... -
On the Processing and Analysis of Microtexts: From Normalization to Semantics
(M D P I AG, 2018-09-18)[Abstract] User-generated content published on microblogging social platforms constitutes an invaluable source of information for diverse purposes: health surveillance, business intelligence, political analysis, etc. We ... -
Parsing as Pretraining
(2020)[Abstract] Recent analyses suggest that encoders pretrained for language modeling capture certain morpho-syntactic structure. However, probing frameworks for word vectors still do not report results on standard setups ... -
Parsing linearizations appreciate PoS tags - but some are fussy about errors
(Association for Computational Linguistics, 2022-11)[Absctract]: PoS tags, once taken for granted as a useful resource for syntactic parsing, have become more situational with the popularization of deep learning. Recent work on the impact of PoS tags on graph- and ... -
Prototipado rápido de un sistema de normalización de tuitsuna aproximación léxica
(Sociedad Española para el Procesamiento del Lenguaje Natural, 2013)[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 ... -
Searching Four-Millennia-Old Documents: A Text Retrieval System for Egyptologists
(2016-08)[Abstract] Progress made in recent years has led to a growing interest in Digital Heritage. This article focuses on Egyptology and, more specifically, the study and preservation of ancient Egyptian scripts. We present a ... -
Seguimiento y análisis automático de contenidos en redes sociales
(Centro Universitario de la Defensa de Marín, 2015)[Abstract]: La Minería de Opiniones es la disciplina que aborda el tratamiento automático de las opiniones contenidas en un texto. Permite, por ejemplo, determinar si en un texto se está opinando o no, o si la polaridad ... -
Semantic Relation Extraction. Resources, Tools and Strategies
(Springer, 2016-07)[Abstract] Relation extraction is a subtask of information extraction that aims at obtaining instances of semantic relations present in texts. This information can be arranged in machine-readable formats, useful for several ... -
Sentiment analysis for reviews and microtexts based on lexico-syntactic knowledge
(BCS-IRSG, 2013)[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 ... -
Sentiment Analysis on Monolingual, Multilingual and Code-Switching Twitter Corpora
(Association for Computational Linguistics, 2015)[Abstract]: We address the problem of performing po- larity classification on Twitter over differ- ent languages, focusing on English and Spanish, comparing three techniques: (1) a monolingual model which knows ... -
Sequence Labeling Parsing by Learning across Representations
(Association for Computational Linguistics, 2019-07)[Absctract]: We use parsing as sequence labeling as a common framework to learn across constituency and dependency syntactic abstractions. To do so, we cast the problem as multitask learning (MTL). First, we show that ... -
Sequence Tagging for Fast Dependency Parsing
(2019)[Abstract] Dependency parsing has been built upon the idea of using parsing methods based on shift-reduce or graph-based algorithms in order to identify binary dependency relations between the words in a sentence. In this ... -
Shallow Recurrent Neural Network for Personality Recognition in Source Code
(CEUR Workshop Proceedings, 2016-12)[Abstract] Personality recognition in source code constitutes a novel task in the field of author profiling on written text. In this paper we describe our proposal for the PR-SOCO shared task in FIRE 2016, which is based ... -
Spanish Resource Grammar Version 2023
(European Language Resources Association (ELRA) & ICCL, 2024)[Abstract]: We present the latest version of the Spanish Resource Grammar (SRG), a grammar of Spanish implemented in the HPSG formalism. Such grammars encode a complex set of hypotheses about syntax making them a resource ... -
Supervised polarity classification of Spanish tweets based on linguistic knowledge
(Association for Computing Machinery, 2013)[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, ... -
Syntactically enriched multilingual sentiment analysis
(CEUR-WS, 2020)[Abstract]: Sentiment analysis of natural language texts needs to deal with linguistic phenomena like negation, intensification or adversative clauses. In this talk, I present an approach to tackle such phenomena by means ... -
The Fragility of Multi-Treebank Parsing Evaluation
(International Committee on Computational Linguistics, 2022-10)[Absctract]: Treebank selection for parsing evaluation and the spurious effects that might arise from a biased choice have not been explored in detail. This paper studies how evaluating on a single subset of treebanks can ... -
TIR over Egyptian Hieroglyphs
(IEEE Computer Society Press, 2016-09)[Abstract] This work presents an Information Retrieval system specifically designed to manage Ancient Egyptian hieroglyphic texts taking into account their peculiarities both at lexical and at encoding level for its ... -
Towards a Graded Dictionary of Spanish Collocations
(Lexical Computing, 2019)[Abstract] Several recent studies have observed that texts of different quality and written by learners at different proficiency levels also vary in the lexical combinations they contain. Such variation can be operationalized ...