Proces. del Leng. Natural, 2021 El sarcasmo se usa con frecuencia para realizar crítica o burla indirecta, a veces hiriendo los sentimientos de alguien. Algunas veces, las personas tienen dificultades para reconocer los comentarios sarcásticos, ya que decimos lo contrario de lo que realmente queremos decir.
Scola, Elsa, Segura-Bedmar, Isabel
openaire +4 more sources
Multi-mode deep auto-encoder recommendation model for fusion of text information
Xi'an Gongcheng Daxue xuebao, 2021 A new recommendation model is proposed to solve the problems of data sparsity and deep semantic information learning when using score information as auxiliary recommendation.
Jinguang CHEN, Xinyi XU, Ganglong FAN
doaj +1 more source
Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT
CoRR, 2020 There is an increasing amount of literature that claims the brittleness of deep neural networks in dealing with adversarial examples that are created maliciously. It is unclear, however, how the models will perform in realistic scenarios where \textit{natural rather than malicious} adversarial instances often exist.
Lichao Sun 0001 +6 more
openaire +2 more sources
A Physics-Informed Modeling of Data Center Cooling and Self-Supervised Learning-Based Autoencoder for Fault Detection and Diagnosis [PDF]
E3S Web of ConferencesEffective Fault Detection and Diagnosis (FDD) is crucial for data center energy efficiency but often struggles with labeled data scarcity. We propose the Physics-Informed Spatio-Temporal Graph (PI-STG) framework, a two-stage self-supervised approach ...
Bonyani Mahdi +2 more
doaj +1 more source
Catchment-scale dissolved carbon concentrations and export estimates across six subarctic streams in northern Sweden [PDF]
Biogeosciences, 2014 Climatic change is currently enhancing permafrost thawing and the flow of water through the landscape in subarctic and arctic catchments, with major consequences for the carbon export to aquatic ecosystems.
R. Giesler +7 more
doaj +1 more source
BERT-of-Theseus: Compressing BERT by Progressive Module Replacing [PDF]
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020 EMNLP ...
Canwen Xu +4 more
openaire +2 more sources
VD-BERT: A Unified Vision and Dialog Transformer with BERT [PDF]
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020 Visual dialog is a challenging vision-language task, where a dialog agent needs to answer a series of questions through reasoning on the image content and dialog history. Prior work has mostly focused on various attention mechanisms to model such intricate interactions.
Yue Wang 0034 +5 more
openaire +2 more sources
Development of a Conceptual Model for Accelerated Project Prioritization after Disaster Event [PDF]
MATEC Web of Conferences, 2019 There is a need for rapid and responsive infrastructure repair and construction after natural disaster events such as hurricanes, wildfires, and tornadoes.
Martins Claudia +3 more
doaj +1 more source
Classification of Russian Texts by Genres Based on Modern Embeddings and Rhythm
Моделирование и анализ информационных систем, 2022 The article investigates modern vector text models for solving the problem of genre classification of Russian-language texts. Models include ELMo embeddings, BERT language model with pre-training and a complex of numerical rhythm features based on lexico-
Ksenia Vladimirovna Lagutina
doaj +1 more source
ABB-BERT: A BERT model for disambiguating abbreviations and contractions
CoRR, 2022 Abbreviations and contractions are commonly found in text across different domains. For example, doctors' notes contain many contractions that can be personalized based on their choices. Existing spelling correction models are not suitable to handle expansions because of many reductions of characters in words.
Prateek Kacker +3 more
openaire +3 more sources