40 citations · 122 across the 13 of their papers we have counts for
16 papers
OCRia-1 Technical Report
Aman Rangapur, Antonio Jimeno Yepes, Daniel Bustamante +4
We introduce OCRia-1, a 4B vision-language model (VLM) for document parsing that excels at preserving table structure, extracting chart data and retaining text formatting. OCRia-1…
Hyperplane bounds for neural feature mappings
Antonio Jimeno Yepes
Deep learning methods minimise the empirical risk using loss functions such as the cross entropy loss. When minimising the empirical risk, the generalisation of the learnt function…
ICDAR 2021 Competition on Scientific Literature Parsing
Antonio Jimeno Yepes, Xu Zhong, Douglas Burdick
Scientific literature contain important information related to cutting-edge innovations in diverse domains. Advances in natural language processing have been driving the fast devel…
Grey-box Adversarial Attack And Defence For Sentiment Classification
Ying Xu, Xu Zhong, Antonio Jimeno Yepes +1
We introduce a grey-box adversarial attack and defence framework for sentiment classification. We address the issues of differentiability, label preservation and input reconstructi…
Single versus Multiple Annotation for Named Entity Recognition of Mutations
David Martinez Iraola, Antonio Jimeno Yepes
The focus of this paper is to address the knowledge acquisition bottleneck for Named Entity Recognition (NER) of mutations, by analysing different approaches to build manually-anno…
Understanding in Artificial Intelligence
Stefan Maetschke, David Martinez Iraola, Pieter Barnard +4
Current Artificial Intelligence (AI) methods, most based on deep learning, have facilitated progress in several fields, including computer vision and natural language understanding…
Elephant in the Room: An Evaluation Framework for Assessing Adversarial Examples in NLP
Ying Xu, Xu Zhong, Antonio Jose Jimeno Yepes +1
An adversarial example is an input transformed by small perturbations that machine learning models consistently misclassify. While there are a number of methods proposed to generat…
Image-based table recognition: data, model, and evaluation
Xu Zhong, Elaheh ShafieiBavani, Antonio Jimeno Yepes
Important information that relates to a specific topic in a document is often organized in tabular format to assist readers with information retrieval and comparison, which may be…
Forget Me Not: Reducing Catastrophic Forgetting for Domain Adaptation in Reading Comprehension
Y. Xu, X. Zhong, A. J. J. Yepes +1
The creation of large-scale open domain reading comprehension data sets in recent years has enabled the development of end-to-end neural comprehension models with promising results…
Global Locality in Biomedical Relation and Event Extraction
Elaheh ShafieiBavani, Antonio Jimeno Yepes, Xu Zhong +1
Due to the exponential growth of biomedical literature, event and relation extraction are important tasks in biomedical text mining. Most work only focus on relation extraction, an…
PubLayNet: largest dataset ever for document layout analysis
Xu Zhong, Jianbin Tang, Antonio Jimeno Yepes
Recognizing the layout of unstructured digital documents is an important step when parsing the documents into structured machine-readable format for downstream applications. Deep n…
Confidence penalty, annealing Gaussian noise and zoneout for biLSTM-CRF networks for named entity recognition
Antonio Jimeno Yepes
Named entity recognition (NER) is used to identify relevant entities in text. A bidirectional LSTM (long short term memory) encoder with a neural conditional random fields (CRF) de…
Named Entity Recognition with stack residual LSTM and trainable bias decoding
Quan Tran, Andrew MacKinlay, Antonio Jimeno Yepes
Recurrent Neural Network models are the state-of-the-art for Named Entity Recognition (NER). We present two innovations to improve the performance of these models. The first innova…
Improving classification accuracy of feedforward neural networks for spiking neuromorphic chips
Antonio Jimeno Yepes, Jianbin Tang, Benjamin Scott Mashford
Deep Neural Networks (DNN) achieve human level performance in many image analytics tasks but DNNs are mostly deployed to GPU platforms that consume a considerable amount of power.…
Knowledge-Based Biomedical Word Sense Disambiguation with Neural Concept Embeddings
A. K. M. Sabbir, Antonio Jimeno Yepes, Ramakanth Kavuluru
Biomedical word sense disambiguation (WSD) is an important intermediate task in many natural language processing applications such as named entity recognition, syntactic parsing, a…
Improving energy efficiency and classification accuracy of neuromorphic chips by learning binary synaptic crossbars
Antonio Jimeno Yepes, Jianbin Tang
Deep Neural Networks (DNN) have achieved human level performance in many image analytics tasks but DNNs are mostly deployed to GPU platforms that consume a considerable amount of p…