Search Results for author:
Found 13 papers, 0 papers with code
Compositional Fusion of Signals in Data Embedding
Embeddings in AI convert symbolic structures into fixed-dimensional vectors, effectively fusing multiple signals.
EXTRACT: Explainable Transparent Control of Bias in Embeddings
We propose EXTRACT: a suite of Explainable and Transparent methods to ConTrol bias in knowledge graph embeddings, so as to assess and decrease the implicit presence of protected information.
QBERT: Generalist Model for Processing Questions
Using a single model across various tasks is beneficial for training and applying deep neural sequence models.
What makes us curious? analysis of a corpus of open-domain questions
In 2017, "We the Curious" science centre in Bristol started a project to capture the curiosity of Bristolians: the project collected more than 10, 000 questions on various topics.
On the Learnability of Concepts: With Applications to Comparing Word Embedding Algorithms
In this paper we introduce the notion of "concept" as a list of words that have shared semantic content.
On Social Machines for Algorithmic Regulation
Autonomous mechanisms have been proposed to regulate certain aspects of society and are already being used to regulate business organisations.
Machine Decisions and Human Consequences
As we increasingly delegate decision-making to algorithms, whether directly or indirectly, important questions emerge in circumstances where those decisions have direct consequences for individual rights and personal opportunities, as well as for the collective good.
Biased Embeddings from Wild Data: Measuring, Understanding and Removing
Many modern Artificial Intelligence (AI) systems make use of data embeddings, particularly in the domain of Natural Language Processing (NLP).
Right for the Right Reason: Training Agnostic Networks
We consider the problem of a neural network being requested to classify images (or other inputs) without making implicit use of a "protected concept", that is a concept that should not play any role in the decision of the network.
History Playground: A Tool for Discovering Temporal Trends in Massive Textual Corpora
Recent studies have shown that macroscopic patterns of continuity and change over the course of centuries can be detected through the analysis of time series extracted from massive textual corpora.
Efficient Classification of Multi-Labelled Text Streams by Clashing
Our method is composed of an online procedure used to efficiently map text into a low-dimensional feature space and a partition of this space into a set of regions for which the system extracts and keeps statistics used to predict multi-label text annotations.
The Anatomy of a Modular System for Media Content Analysis
As part of our ongoing effort in automating media content analysis for the social sciences, we have built a modular system by combining multiple AI modules into a flexible framework in which they can cooperate in complex tasks.
