BackExaminar Comunicaciones por departamento (eus.) "Hizkuntza eta sistema informatikoak"
Now showing items 1-20 of 24
-
A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings
; Labaka Intxauspe, Gorka
; Agirre Bengoa, Eneko (ACL, 2018)
Recent work has managed to learn cross-lingual word embeddings without parallel data by mapping monolingual embeddings to a shared space through adversarial training. However, their evaluation has focused on favorable ... -
An Effective Approach to Unsupervised Machine Translation
; Labaka Intxauspe, Gorka; Agirre Bengoa, Eneko (ACL, 2019)
While machine translation has traditionally relied on large amounts of parallel corpora, a recent research line has managed to train both Neural Machine Translation (NMT) and Statistical Machine Translation (SMT) systems ... -
Behavioral anomaly detection system for the wellbeign assessment and lifestyle support of older people at home
(Elsevier B.V, 2021)The wellbeing assessment of older people is becoming crucial in today’s era of aging and home care in order to provide the best possible care. New technologies are being used to assist older people at home, which generates ... -
Bilingual Lexicon Induction through Unsupervised Machine Translation
; Labaka Intxauspe, Gorka; Agirre Bengoa, Eneko (ACL, 2019)
A recent research line has obtained strong results on bilingual lexicon induction by aligning independently trained word embeddings in two languages and using the resulting cross-lingual embeddings to induce word translation ... -
Extending Fairness Expressibility of ECTL+: A Tree-Style One-Pass Tableau Approach
(Schloss Dagstuhl – Leibniz-Zentrum für Informatik, 2018-10-08)Temporal logic has become essential for various areas in computer science, most notably for the specification and verification of hardware and software systems. For specification purposes rich temporal languages are required ... -
Generalizing and Improving Bilingual Word Embedding Mappings with a Multi-Step Framework of Linear Transformations
; Labaka Intxauspe, Gorka; Agirre Bengoa, Eneko (Association for the Advancement of Artificial Intelligence, 2018)
Using a dictionary to map independently trained word embeddings to a shared space has shown to be an effective approach to learn bilingual word embeddings. In this work, we propose a multi-step framework of linear ... -
Improving Dependency Parsing with Semantic Classes
Agirre Bengoa, Eneko; ; Gojenola Galletebeitia, Koldobika ; (Association for Computational Linguistics, 2011)
En este artículo se presenta la introducción de clases semánticas de WordNet en un analizador de dependencias, obteniendo mejoras en el Penn Treebank completo por primera vez. Probamos diferentes combinaciones de algunas ... -
Label Verbalization and Entailment for Effective Zero and Few-Shot Relation Extraction
Sainz Jiménez, Oscar; López de Lacalle Lecuona, Oier ; Labaka Intxauspe, Gorka ; Barrena Madinabeitia, Ander ; Agirre Bengoa, Eneko (ACL, 2021)
Relation extraction systems require large amounts of labeled examples which are costly to annotate. In this work we reformulate relation extraction as an entailment task, with simple, hand-made, verbalizations of relations ... -
Learning bilingual word embeddings with (almost) no bilingual data
; Labaka Intxauspe, Gorka; Agirre Bengoa, Eneko (ACL, 2017)
Most methods to learn bilingual word embeddings rely on large parallel corpora, which is difficult to obtain for most language pairs. This has motivated an active research line to relax this requirement, with methods that ... -
Learning principled bilingual mappings of word embeddings while preserving monolingual invariance
; Labaka Intxauspe, Gorka; Agirre Bengoa, Eneko (2016)
Mapping word embeddings of different languages into a single space has multiple applications. In order to map from a source space into a target space, a common approach is to learn a linear mapping that minimizes the ... -
OLYMPUS: An intelligent interactive learning platform for procedural tasks
(ScitePress, 2012)Providing Interactive Systems with educational capabilities is essential in order to achieve real effectiveness in simulation based training. However, the development cost of adding intelligence to those systems is huge. ... -
On WordNet semantic classes and dependency parsing
; Agirre Bengoa, Eneko; ; ; Gojenola Galletebeitia, Koldobika (ACL, 2014)
Este artículo presenta experimentos con clases semánticas de WordNet para mejorar el análisis de dependencias. Estudiamos el efecto de las clases semánticas en tres analizadores de dependencias, utilizando dos tipos de ... -
One-Pass Context-Based Tableaux Systems for CTL and ECTL
(Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2020-09-25)When building tableau for temporal logic formulae, applying a two-pass construction, we first check the validity of the given tableaux input by creating a tableau graph, and then, in the second “pass”, we check if all the ... -
Personalized Nutritional Guidance System to Prevent Malnutrition in Pluripathological Older Patients
(SciTePress, 2022)Malnutrition is a frequent problem in the elderly population, who usually is affected by one or more pathologies. The health status of these patients can get worsened if malnutrition is left untreated. Nutritional guidelines ... -
Pixel-Level Quality Indicator for Image Data Annotation
(IEEE, 2024-09-05)The creation of image classification and segmentation Machine Learning products requires the annotation of different classes by experts as well as the management of large volumes of data. This paper introduces a new ... -
Principled Paraphrase Generation with Parallel Corpora
; ; Soroa Echave, Aitor; Labaka Intxauspe, Gorka ; Agirre Bengoa, Eneko (ACL, 2022)
Round-trip Machine Translation (MT) is a popular choice for paraphrase generation, which leverages readily available parallel corpora for supervision. In this paper, we formalize the implicit similarity function induced ... -
Semantic Web Technology for Agent Communication Protocols.
; Bermúdez de Andrés, Jesús; ; Illarramendi Echave, María Aránzazu (Springer, 2008)
One relevant aspect in the development of the Semantic Web framework is the achievement of a real inter-agents communication capability at the semantic level. The agents should be able to communicate and understand each ... -
SemEval-2015 Task 2: Semantic Textual Similarity, English, Spanish and Pilot on Interpretability
Agirre Bengoa, Eneko; ; ; ; ; ; ; López Gazpio, Iñigo ; Marichalar Anglada, Montserrat ; ; Rigau Claramunt, Germán ; Uria Garin, Larraitz ; (SemEval, 2015)
In semantic textual similarity (STS), systems rate the degree of semantic equivalence between two text snippets. This year, the participants were challenged with new datasets in English and Spanish. The annotations for ... -
SPIN at MentalRiskES 2023: Transformer-Based Model for Real-Life Depression Detection in Messaging Apps
; Justo Blanco, Raquel (CEUR-WS, 2023)
Depression is a prevalent and severe mental health condition that significantly impacts global population, causing personal suffering and reduced quality of life. Its symptoms are often visible on social media and digital ... -
Towards Certified Model Checking for PLTL Using One-Pass Tableaux
(Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2019-10-19)The standard model checking setup analyses whether the given system specification satisfies a dedicated temporal property of the system, providing a positive answer here or a counter-example. At the same time, it is often ...