2022
Huertas-García, Álvaro; Martín, Alejandro; Huertas-Tato, Javier; Camacho, David
Exploring Dimensionality Reduction Techniques in Multilingual Transformers Miscellaneous
CoRR, 2022.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Computational Intelligence, Deep Learning, Embeddings, Feature Selection, Machine Learning, Natural Language Processing, Sentence alignment, Text Analysis, Transformers
@misc{nokey,
title = {Exploring Dimensionality Reduction Techniques in Multilingual Transformers},
author = {Álvaro Huertas-García and Alejandro Martín and Javier Huertas-Tato and David Camacho},
url = {https://doi.org/10.48550/arxiv.2204.08415},
doi = {10.48550/ARXIV.2204.08415},
year = {2022},
date = {2022-04-18},
urldate = {2022-04-18},
abstract = {Both in scientific literature and in industry,, Semantic and context-aware Natural Language Processing-based solutions have been gaining importance in recent years. The possibilities and performance shown by these models when dealing with complex Language Understanding tasks is unquestionable, from conversational agents to the fight against disinformation in social networks. In addition, considerable attention is also being paid to developing multilingual models to tackle the language bottleneck. The growing need to provide more complex models implementing all these features has been accompanied by an increase in their size, without being conservative in the number of dimensions required. This paper aims to give a comprehensive account of the impact of a wide variety of dimensional reduction techniques on the performance of different state-of-the-art multilingual Siamese Transformers, including unsupervised dimensional reduction techniques such as linear and nonlinear feature extraction, feature selection, and manifold techniques. In order to evaluate the effects of these techniques, we considered the multilingual extended version of Semantic Textual Similarity Benchmark (mSTSb) and two different baseline approaches, one using the pre-trained version of several models and another using their fine-tuned STS version. The results evidence that it is possible to achieve an average reduction in the number of dimensions of 91.58%±2.59% and 54.65%±32.20%, respectively. This work has also considered the consequences of dimensionality reduction for visualization purposes. The results of this study will significantly contribute to the understanding of how different tuning approaches affect performance on semantic-aware tasks and how dimensional reduction techniques deal with the high-dimensional embeddings computed for the STS task and their potential for highly demanding NLP tasks },
howpublished = {CoRR},
keywords = {Artificial Intelligence, Computational Intelligence, Deep Learning, Embeddings, Feature Selection, Machine Learning, Natural Language Processing, Sentence alignment, Text Analysis, Transformers},
pubstate = {published},
tppubtype = {misc}
}
2021
Huertas-García, Álvaro; Huertas-Tato, Javier; Martín, Alejandro; Camacho, David
CIVIC-UPM at CheckThat! 2021: Integration of Transformers in Misinformation Detection and Topic Classification Proceedings Article
In: Conference and Labs of the Evaluation Forum (CLEF) Working Notes, pp. 520–530, 2021.
Abstract | Links | BibTeX | Tags: Computational Intelligence, Deep Learning, Disinformation, Information Distortion, Machine Learning, Natural Language Processing, Social Networks, Text Analysis, Transformers
@inproceedings{huertas-garcia_civic-upm_2021,
title = {CIVIC-UPM at CheckThat! 2021: Integration of Transformers in Misinformation Detection and Topic Classification},
author = {Álvaro Huertas-García and Javier Huertas-Tato and Alejandro Martín and David Camacho},
url = {http://ceur-ws.org/Vol-2936/paper-41.pdf},
year = {2021},
date = {2021-05-24},
urldate = {2021-05-24},
booktitle = {Conference and Labs of the Evaluation Forum (CLEF) Working Notes},
pages = {520--530},
abstract = {Online Social Networks (OSNs) growth enables and amplifies the quick spread of harmful, manipulative and false information that influence public opinion while sow conflict on social or political issues. Therefore, the development of tools to detect malicious actors and to identify low-credibility information and misinformation sources is a new crucial challenge in the ever-evolving field of Artificial Intelligence. The scope of this paper is to present a Natural Language Processing (NLP) approach that uses Doc2Vec and different state-of-the-art transformer-based models for the CLEF2021 Checkthat! lab Task 3. Through this approach, the results show that it is possible to achieve 41.43% macro-average F1-score in the misinformation detection (Task A) and 67.65% macro-average F1-score in the topic classification (Task B).},
keywords = {Computational Intelligence, Deep Learning, Disinformation, Information Distortion, Machine Learning, Natural Language Processing, Social Networks, Text Analysis, Transformers},
pubstate = {published},
tppubtype = {inproceedings}
}
2011
Camacho, David; Granados, Ana; Cebrián, Manuel; Rodríguez, Francisco Borja
Reducing the Loss of Information through Annealing Text Distortion Journal Article
In: IEEE Transactions on Knowledge and Data Engineering, vol. 23, no. 7, pp. 1090-1102, 2011, ISSN: 1041-4347.
Links | BibTeX | Tags: Clustering, Data Compression, Data Mining, Text Analysis
@article{5582094,
title = {Reducing the Loss of Information through Annealing Text Distortion},
author = {David Camacho and Ana Granados and Manuel Cebrián and Francisco Borja Rodríguez},
url = {http://dx.doi.org/10.1109/TKDE.2010.173},
issn = {1041-4347},
year = {2011},
date = {2011-07-01},
urldate = {2011-07-01},
journal = {IEEE Transactions on Knowledge and Data Engineering},
volume = {23},
number = {7},
pages = {1090-1102},
publisher = {IEEE Press},
keywords = {Clustering, Data Compression, Data Mining, Text Analysis},
pubstate = {published},
tppubtype = {article}
}