Search Results for author: Marc Franco-Salvador

Found 18 papers, 5 papers with code

Zero and Few-shot Learning for Author Profiling

no code implementations22 Apr 2022 Mara Chinea-Rios, Thomas Müller, Gretel Liz De la Peña Sarracén, Francisco Rangel, Marc Franco-Salvador

We find that entailment-based models out-perform supervised text classifiers based on roberta-XLM and that we can reach 80% of the accuracy of previous approaches using less than 50\% of the training data on average.

Few-Shot Learning

Active Few-Shot Learning with FASL

1 code implementation20 Apr 2022 Thomas Müller, Guillermo Pérez-Torró, Angelo Basile, Marc Franco-Salvador

Recent advances in natural language processing (NLP) have led to strong text classification models for many tasks.

Active Learning Few-Shot Learning +1

Unsupervised Ranking and Aggregation of Label Descriptions for Zero-Shot Classifiers

no code implementations20 Apr 2022 Angelo Basile, Marc Franco-Salvador, Paolo Rosso

Zero-shot text classifiers based on label descriptions embed an input text and a set of labels into the same space: measures such as cosine similarity can then be used to select the most similar label description to the input text as the predicted label.

Few-Shot Learning with Siamese Networks and Label Tuning

1 code implementation ACL 2022 Thomas Müller, Guillermo Pérez-Torró, Marc Franco-Salvador

We study the problem of building text classifiers with little or no training data, commonly known as zero and few-shot text classification.

Few-Shot Learning Few-Shot Text Classification +2

What Motivates You? Benchmarking Automatic Detection of Basic Needs from Short Posts

no code implementations ACL 2021 Sanja Stajner, Seren Yenikent, Bilal Ghanem, Marc Franco-Salvador

According to the self-determination theory, the levels of satisfaction of three basic needs (competence, autonomy and relatedness) have implications on people{'}s everyday life and career.


Five Psycholinguistic Characteristics for Better Interaction with Users

no code implementations17 Dec 2020 Sanja Štajner, Seren Yenikent, Marc Franco-Salvador

When two people pay attention to each other and are interested in what the other has to say or write, they almost instantly adapt their writing/speaking style to match the other.

Aspect On: an Interactive Solution for Post-Editing the Aspect Extraction based on Online Learning

no code implementations LREC 2020 Mara Chinea-Rios, Marc Franco-Salvador, Yassine Benajiba

Experimental results show that Aspect On dramatically reduces the number of user clicks and effort required to post-edit the aspects extracted by the model.

Aspect Extraction online learning

UH-PRHLT at SemEval-2016 Task 3: Combining Lexical and Semantic-based Features for Community Question Answering

no code implementations SEMEVAL 2016 Marc Franco-Salvador, Sudipta Kar, Thamar Solorio, Paolo Rosso

In this work we describe the system built for the three English subtasks of the SemEval 2016 Task 3 by the Department of Computer Science of the University of Houston (UH) and the Pattern Recognition and Human Language Technology (PRHLT) research center - Universitat Polit`ecnica de Val`encia: UH-PRHLT.

Community Question Answering Knowledge Graphs

Semantically-informed distance and similarity measures for paraphrase plagiarism identification

no code implementations29 May 2018 Miguel A. Álvarez-Carmona, Marc Franco-Salvador, Esaú Villatoro-Tello, Manuel Montes-y-Gómez, Paolo Rosso, Luis Villaseñor-Pineda

Paraphrase plagiarism identification represents a very complex task given that plagiarized texts are intentionally modified through several rewording techniques.

A Resource-Light Method for Cross-Lingual Semantic Textual Similarity

1 code implementation19 Jan 2018 Goran Glavaš, Marc Franco-Salvador, Simone Paolo Ponzetto, Paolo Rosso

In contrast, we propose an unsupervised and a very resource-light approach for measuring semantic similarity between texts in different languages.

Cross-Lingual Semantic Textual Similarity Information Retrieval +6

A Low Dimensionality Representation for Language Variety Identification

1 code implementation30 May 2017 Francisco Rangel, Marc Franco-Salvador, Paolo Rosso

We compare our LDR method with common state-of-the-art representations and show an increase in accuracy of ~35%.

Cannot find the paper you are looking for? You can Submit a new open access paper.