Dr. Javier Huertas

@article{huertas-tato_silt_2022,

title = {SILT: Efficient transformer training for inter-lingual inference},

author = {Javier Huertas-Tato and Alejandro Martín and David Camacho},

url = {https://www.sciencedirect.com/science/article/pii/S0957417422003578},

doi = {10.1016/j.eswa.2022.116923},

issn = {0957-4174},

year  = {2022},

date = {2022-08-01},

urldate = {2022-08-01},

journal = {Expert Systems with Applications},

volume = {200},

pages = {116923},

abstract = {The ability of transformers to perform precision tasks such as question answering, Natural Language Inference (NLI) or summarizing, has enabled them to be ranked as one of the best paradigms to address Natural Language Processing (NLP) tasks. NLI is one of the best scenarios to test these architectures, due to the knowledge required to understand complex sentences and established relationships between a hypothesis and a premise. Nevertheless, these models suffer from the incapacity to generalize to other domains or from difficulties to face multilingual and interlingual scenarios. The leading pathway in the literature to address these issues involve designing and training extremely large architectures, but this causes unpredictable behaviors and establishes barriers which impede broad access and fine tuning. In this paper, we propose a new architecture called Siamese Inter-Lingual Transformer (SILT). This architecture is able to efficiently align multilingual embeddings for Natural Language Inference, allowing for unmatched language pairs to be processed. SILT leverages siamese pre-trained multi-lingual transformers with frozen weights where the two input sentences attend to each other to later be combined through a matrix alignment method. The experimental results carried out in this paper evidence that SILT allows to reduce drastically the number of trainable parameters while allowing for inter-lingual NLI and achieving state-of-the-art performance on common benchmarks.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{martin_facter-check_2022,

title = {FacTeR-Check: Semi-automated fact-checking through Semantic Similarity and Natural Language Inference},

author = {Alejandro Martín and Javier Huertas-Tato and Álvaro Huertas-García and Guillermo Villar-Rodríguez and David Camacho},

url = {http://arxiv.org/abs/2110.14532},

year  = {2022},

date = {2022-02-01},

urldate = {2022-02-01},

journal = {arXiv:2110.14532 [cs]},

abstract = {Our society produces and shares overwhelming amounts of information through Online Social Networks (OSNs). Within this environment, misinformation and disinformation have proliferated, becoming a public safety concern in most countries. Allowing the public and professionals to efficiently find reliable evidences about the factual veracity of a claim is a crucial step to mitigate this harmful spread. To this end, we propose FacTeR-Check, a multilingual architecture for semi-automated fact-checking that can be used for either applications designed for the general public and by fact-checking organisations. FacTeR-Check enables retrieving fact-checked information, unchecked claims verification and tracking dangerous information over social media. This architectures involves several modules developed to evaluate semantic similarity, to calculate natural language inference and to retrieve information from Online Social Networks. The union of all these components builds a semi-automated fact-checking tool able of verifying new claims, to extract related evidence, and to track the evolution of a hoax on a OSN. While individual modules are validated on related benchmarks (mainly MSTS and SICK), the complete architecture is validated using a new dataset called NLI19-SP that is publicly released with COVID-19 related hoaxes and tweets from Spanish social media. Our results show state-of-the-art performance on the individual benchmarks, as well as producing a useful analysis of the evolution over time of 61 different hoaxes.},

note = {arXiv: 2110.14532},

keywords = {},

pubstate = {published},

tppubtype = {article}

}