Mathias Verbeke

Kernel-Based logical and relational learning with klog for hedge cue detection

Hedge cue detection is a Natural Language Processing (NLP) task that consists of determining whether sentences contain hedges. These linguistic devices indicate that authors do not or cannot back up their opinions or statements with facts. This binary classification problem, i.e. distinguishing factual versus uncertain sentences, only recently received attention in the NLP community. We use kLog, a new logical and relational language for kernel-based learning, to tackle this problem. We present results on the CoNLL 2010 benchmark dataset that consists of a set of paragraphs from Wikipedia, one of the domains in which uncertainty detection has become important. Our approach shows competitive results compared to state-of-the-art systems.

kLogNLP: Graph Kernel--based Relational Learning of Natural Language

kLog is a framework for kernel-based learning that has already proven successful in solving a number of relational tasks in natural language processing. In this paper, we present kLogNLP, a natural language processing module for kLog. This module enriches kLog with NLP-specific preprocessors, enabling the use of existing libraries and toolkits within an elegant and powerful declarative machine learning framework. The resulting relational model of the domain can be extended by specifying additional relational features in a declarative way using a logic programming language. This declarative approach offers a flexible way of experimentation and a way to insert domain knowledge.

KUL-Eval: A Combinatory Categorial Grammar Approach for Improving Semantic Parsing of Robot Commands using Spatial Context

When executing commands, a robot has a certain level of contextual knowledge about the environment in which it operates. Taking this knowledge into account can be beneficial to disambiguate commands with multiple interpretations. We present an approach that uses combinatory categorial grammars for improving the semantic parsing of robot commands that takes into account the spatial context of the robot. The results indicate a clear improvement over non-contextual semantic parsing. This work was done in the context of the SemEval-2014 task on supervised semantic parsing of spatial robot commands.

Relational regularization and feature ranking

Regularization is one of the key concepts in machine learning, but so far it has received only little attention in the logical and relational learning setting. Here we propose a regularization and feature selection technique for such setting, in which one commonly represents the structure of the domain using an entity-relationship model. To this end, we introduce a notion of locality that ties together features according to their proximity in a transformed representation of the relational learning problem obtained via a procedure that we call “graphicalization”. We present two techniques, a wrapper and an efficient embedded approach, to identify the most relevant sets of predicates which yields more readily interpretable results than selecting low-level propositionalized features. The proposed techniques are implemented in the kernel-based relational learner kLog, although the ideas presented here can also be adapted to other relational learning frameworks. We evaluate our approach on classification tasks in the natural language processing and bioinformatics

Critical news reading with Twitter? Exploring data-mining practices and their impact on societal discourse

Abstract This article shows that the collaboration between social science and computer science scholars proves fruitful in enhancing conceptual and methodological innovation in research appropriate for the digital world. It presents arguments for ways in which a multi-disciplinary approach can strengthen media studies and nnovatively advance both research breadth and depth. To illustrate this interesting connection of both disciplines, we present the example analysis of large data from Twitter and discuss this analysis in a communication science research environment. We propose TwiNeR, a software tool that analyzes tweet content using an advanced language modeling approach for classifying tweets into five prototypical messages referring to ‘activities’ related to news and news sources in the Twitter network (i.e., source-fed article, user-fed article, content spread by user, other source content, other user content).

Lazy and Eager Relational Learning Using Graph-Kernels

Machine learning systems can be distinguished along two dimensions. The first is concerned with whether they deal with a feature based (propositional) or a relational representation; the second with the use of eager or lazy learning techniques. The advantage of relational learning is that it can capture structural information. We compare several machine learning techniques along these two dimensions on a binary sentence classification task (hedge cue detection). In particular, we use SVMs for eager learning, and \(k\)NN for lazy learning. Furthermore, we employ kLog, a kernel-based statistical relational learning framework as the relational framework. Within this framework we also contribute a novel lazy relational learning system. Our experiments show that relational learners are particularly good at handling long sentences, because of long distance dependencies.

How to Carve up the World: Learning and Collaboration for Structure Recommendation

Structuring is one of the fundamental activities needed to understand data. Human structuring activity lies behind many of the datasets found on the internet that contain grouped instances, such as file or email folders, tags and bookmarks, ontologies and linked data. Understanding the dynamics of large-scale structuring activities is a key prerequisite for theories of individual behaviour in collaborative settings as well as for applications such as recommender systems. One central question is to what extent the “structurer” – be it human or machine – is driven by his/its own prior structures, and to what extent by the structures created by others such as one’s communities.