Search
Search Results
-
Ontologies and Conceptual Graphs
In the previous chapter, we have presented Description Logics. In this chapter, we turn to ontologies, i.e., “ ‘implementation versions’ of...
-
Hints and Expected Results for Exercises
Task 1 requires data on the frequency of words. We, therefore, need frequency lists of English words (see p. 213). It also requires comparing...
-
XML, TEI, CDL
In this chapter, we will consider the eXtensible Markup Language (XML) and three of its applications relevant to Natural Language Processing: the...
-
Self-supervised and Multilingual Learning Applied to the Wolof, Swahili and Fongbe
Under-resourced languages face significant challenges in speech recognition due to limited resources and data availability, hampering their...
-
A New Hybrid Algorithm Based on Ant Colony Optimization and Recurrent Neural Networks with Attention Mechanism for Solving the Traveling Salesman Problem
In this paper, we propose a hybrid approach for solving the symmetric traveling salesman problem. The proposed approach combines the ant colony...
-
Convolutional Neural Network Based Detection Approach of Undesirable SMS (Short Message Service) in the Cameroonian Context
With the low cost of mobile phones, SMS(Short Message Service) and the advent of communications software (whatsapp, telegram, etc.), many people...
-
Explaining Meta-learner’s Predictions: Case of Corporate CO2 Emissions
Production activities of companies very often leads to release of carbon dioxide (CO...
-
Two High Capacity Text Steganography Schemes Based on Color Coding
Text steganography is a mechanism of hiding secret text message inside another text as a covering message. In this paper, we propose a text...
-
A Hybrid Algorithm Based on Tabu Search and K-Means for Solving the Traveling Salesman Problem
In this paper, we propose an approach to solve the symmetric Traveling Salesman Problem (TSP) by combining the K-means clustering technique and tabu...
-
Recurrent Neural Network Parallelization for Hate Messages Detection
Hate speech is a threat to democratic values, because it stimulates incitement to discrimination, which international law prohibits. To limit the...
-
Temporal Modification of Event Kinds
As the counterpart to kinds of entities or objects [5], event kinds are used to account for a variety of linguistic facts in the event domain. The...
-
Sentence-Final Particle de in Mandarin as an Informativity Maximizer
In this study, we provide a new empirical generalization of the meaning contribution of the Mandarin sentence-final particle de from an information...
-
Silence, Dissent, and Common Ground
In a certain picture of cooperative conversation, ‘silence gives assent’. However, in adversarial contexts, structured by power dynamics, silence may...
-
Formalizing Henkin-Style Completeness of an Axiomatic System for Propositional Logic
I formalize a Henkin-style completeness proof for an axiomatic system for propositional logic in the proof assistant Isabelle/HOL. The formalization...
-
Deep Learning Can Recognize Complex Relationships
For more complex problems, simple linear models are insufficient. A way out is offered by models with several nonlinear layers (operators), which can...
-
Image Recognition with Deep Neural Networks
Image recognition is about finding automatic methods to identify objects and their arrangement in an image or photo. This includes classifying the...
-
XentricAI: A Gesture Sensing Calibration Approach Through Explainable and User-Centric AI
Gesture recognition systems offering contactless human-machine interaction have diverse applications, from smart homes to healthcare. However, they...
-
Categorical Foundation of Explainable AI: A Unifying Theory
Explainable AI (XAI) aims to address the human need for safe and reliable AI systems. However, numerous surveys emphasize the absence of a sound...
-
Model Guidance via Explanations Turns Image Classifiers into Segmentation Models
Heatmaps generated on inputs of image classification networks via explainable AI methods like Grad-CAM and LRP have been observed to resemble...
-
Model-Agnostic Knowledge Graph Embedding Explanations for Recommender Systems
Explanations in recommender systems play an essential role in enhancing transparency, trust, and persuasiveness. In that regard, Knowledge Graphs...