Listar Lingua e Sociedade da Información (Language in the Information Society) (LYS) por título
Mostrando ítems 99-116 de 116
-
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 ... -
The Impact of Edge Displacement Vaserstein Distance on UD Parsing Performance
(The MIT Press, 2022)[Abstract] We contribute to the discussion on parsing performance in NLP by introducing a measurement that evaluates the differences between the distributions of edge displacement (the directed distance of edges) seen in ... -
The megaphone of the people? Spanish SentiStrength for real-time analysis of political tweets
(SAGE Publications & CILIP, 2015)[Abstract]: Twitter is an important platform for sharing opinions about politicians, parties and political decisions. These opinions can be exploited as a source of information to monitor the impact of politics on society. ... -
The scaling of the minimum sum of edge lengths in uniformly random trees
(2016-06)[Abstract] The minimum linear arrangement problem on a network consists of finding the minimum sum of edge lengths that can be achieved when the vertices are arranged linearly. Although there are algorithms to solve this ... -
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 ... -
Towards fast natural language parsing: FASTPARSE ERC Starting Grant
(Sociedad Española para el Procesamiento del Lenguaje Natural (SEPLN), 2017-09)[Abstract:] The goal of the FASTPARSE project (Fast Natural Language Parsing for Large-Scale NLP), funded by the European Research Council (ERC), is to achieve a breakthrough in the speed of natural language syntactic ... -
Towards Making a Dependency Parser See
(Association for Computational Linguistics, 2019-11)[Absctract]: We explore whether it is possible to leverage eye-tracking data in an RNN dependency parser (for English) when such information is only available during training - i.e. no aggregated or token-level gaze features ... -
Towards Robust Word Embeddings for Noisy Texts
(MDPI, 2020)[Abstract] Research on word embeddings has mainly focused on improving their performance on standard corpora, disregarding the difficulties posed by noisy texts in the form of tweets and other types of non-standard writing ... -
Towards the Automatic Construction of a Multilingual Dictionary of Collocations using Distributional Semantics
(Lexical Computing, 2019)[Abstract] This paper presents the method used to create a multilingual online dictionary of collocations of English, Portuguese, and Spanish. This resource is built automatically and contains three types of collocations: ... -
Transition-based Semantic Dependency Parsing with Pointer Networks
(Association for Computational Linguistics (ACL), 2020-07)[Abstract]: Transition-based parsers implemented with Pointer Networks have become the new state of the art in dependency parsing, excelling in producing labelled syntactic trees and outperforming graph-based models in ... -
Transition-based semantic role labeling with pointer networks
(Elsevier, 2023-01-25)[Abstract] Semantic role labeling (SRL) focuses on recognizing the predicate–argument structure of a sentence and plays a critical role in many natural language processing tasks such as machine translation and question ... -
Tratamiento sintáctico de la negación en análisis del sentimiento monolingüe y multilingüe
(2017-09-19)[Abstract] Dealing with negation in a proper way is a relevant factor in order to obtain high performance sentiment analysis systems. In this framework, we present a method for the treatment of negation in Spanish that ... -
Uma Utilidade para o Reconhecimento de Topónimos em Documentos Medievais
(Universidade do Minho, 2019)[Resumo] Este artigo apresenta o método de construçao duma ferramenta para a anotaçao de entidades geográficas mencionadas em textos medievais. A nova ferramenta foi desenvolvida a partir dos módulos de língua contemporanea ... -
Universal, unsupervised (rule-based), uncovered sentiment analysis
(Elsevier, 2017-02)[Abstract]: We present a novel unsupervised approach for multilingual sentiment analysis driven by compositional syntax-based rules. On the one hand, we exploit some of the main advantages of unsupervised algorithms: (1) ... -
Unveiling factors influencing judgment variation in sentiment analysis with natural language processing and statistics
(Public Library of Science, 2024-05)[Abstract]: TripAdvisor reviews and comparable data sources play an important role in many tasks in Natural Language Processing (NLP), providing a data basis for the identification and classification of subjective judgments, ... -
UzbekVerbDetection: Rule-based Detection of Verbs in Uzbek Texts
(European Language Resources Association (ELRA) & ICCL, 2024)[Abstract]: Verb detection is a fundamental task in natural language processing that involves identifying the action or state expressed by a verb in a sentence. However, in Uzbek language, verb detection is challenging due ... -
Viable Dependency Parsing as Sequence Labeling
(Association for Computational Linguistics (ACL), 2019-06)[Abstract]: We recast dependency parsing as a sequence labeling problem, exploring several encodings of dependency trees as labels. While dependency parsing by means of sequence labeling had been attempted in existing work, ...