Search

We present a neural network architecture focused on verifying facts against evidence found in a knowledge base. The architecture can perform relevance evaluation and claim verification, parts of a well-known three-stage method of fact-checking. We fine-tuned BERT to codify claims and pieces of evidence separately. An attention layer between the claim and evidence representation computes alignment scores to identify relevant terms between both. Finally, a classification layer receives the vector representation of claims and evidence and performs the relevance and verification classification. Our model allows a more straightforward interpretation of the predictions than other state-of-the-art models. We use the scores computed within the attention layer to show which evidence spans are more relevant to classify a claim as supported or refuted. Our classification models achieve results compared to the state-of-the-art models in terms of classification of relevance evaluation and claim verification accuracy on the FEVER dataset. [ABSTRACT FROM AUTHOR]

This work presents an experimental study on the task of Named Entity Recognition (NER) for a narrow domain in Spanish language. This study considers two approaches commonly used in this kind of problem, namely, a Conditional Random Fields (CRF) model and Recurrent Neural Network (RNN). For the latter, we employed a bidirectional Long Short-Term Memory with ELMO's pre-trained word embeddings for Spanish. The comparison between the probabilistic model and the deep learning model was carried out in two collections, the Spanish dataset from CoNLL-2002 considering four classes under the IOB tagging schema, and a Mexican Spanish news dataset with seventeen classes under IOBES schema. The paper presents an analysis about the scalability, robustness, and common errors of both models. This analysis indicates in general that the BiLSTM-ELMo model is more suitable than the CRF model when there is "enough" training data, and also that it is more scalable, as its performance was not significantly affected in the incremental experiments (by adding one class at a time). On the other hand, results indicate that the CRF model is more adequate for scenarios having small training datasets and many classes. [ABSTRACT FROM AUTHOR]