
Richard BergmairIndependent Researcher
Richard Bergmair
Doctor of Philosophy
About
17
Publications
904
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
186
Citations
Additional affiliations
Education
October 2006 - July 2010
October 2005 - July 2006
September 2003 - July 2004
Publications
Publications (17)
This thesis develops several pieces of theory and computational techniques which can be deployed for the purpose of allowing a computer to analyze short pieces of text (e.g. "Socrates is a man and every man is mortal.") and, on the basis of such an analysis, to decide yes/no questions about the text ("Is Socrates mortal?"). More particularly, the p...
We outline problems with the interpretation of accuracy in the presence of bias, arguing that the issue is a particularly pressing concern for RTE evaluation. Furthermore, we argue that average precision scores are unsuitable for RTE, and should not be reported. We advocate mutual information as a new evaluation measure that should be reported in a...
The polymorphy described above sits at the core of this discussion. To show this more clearly, a type of logic will be established, but instead of reasoning, and determining whether something is true or false, it will make moral judgments, telling whether something is good or bad. Some core thoughts of positivistic and teleological ethics will be f...
The Monte Carlo Pseudo Inference Engine for Text (MCPIET) addresses the RTE problem within a new theoretic framework for robust inference and logical pattern processing based on integrated deep and shallow semantics. In this report we outline, in some detail, this new theoretic framework, and we will use it to shed some light on the informa-tivity...
In this paper, we address the problem of searching for or filtering electronic documents in large collections such as the world wide web. This will be framed as an economic resource allocation problem, while invoking automatic retrieval engines as a non-market pricing mechanism. For information retrieval, this point of view helps illuminate many im...
In this paper, we will attempt to give a comprehensive bibliographic account of the work in linguistic steganography published up to date. As the field is still in its infancy there is no widely accepted publi-cation venue. Relevant work on the subject is scattered throughout the literature on information security, information hiding, imaging and w...
We introduce content-aware steganography as a new paradigm of steganography stemming from a shift in perspectives towards the objects of steganography. In particular, we abandon the point of view that steganographic objects can be con- sidered pieces of data, suggesting that they should rather be considered pieces of information. We provide some ev...
A grammatical framework is presented that augments context-free production rules with semantic production rules that rely on fuzzy relations as representations of fuzzy natural language concepts. It is shown how the well-known technique of syntax-driven semantic analysis can be used to infer from an expression in a language defined in such a semant...
We outline the linguistic problem of word-sense ambiguity and demonstrate its relevance to current computer security applications
in the context of Human Interactive Proofs (HIPs). Such proofs enable a machine to automatically determine whether it is interacting
with another machine or a human. HIPs were recently proposed to fight abuse of web serv...
One well-known design principle guiding the construction of neural networks is that a feed-forward network will be able to filter noise when few hidden units are used. Another design principle states that a network will be able to solve more complex problems when many hidden units are used. The experimental setup presented herein aims at analyzing...
In this article we use methodologies commonly used in computer science to illuminate some long-standing problems of ethics. We point out an interesting isomorphism between normative ethics and systematic reasoning as studied in the context of artificial intelligence, and demonstrate the relevance of some results from game theory to ethical reasonin...
We outline the linguistic problem of word-sense ambiguity and demonstrate its relevance to current computer security applications in the context of Human Interactive Proofs (HIPs). Such proofs enable a machine to automatically determine whether it is interacting with another machine or a human. HIPs were recently proposed to fight abuse of web serv...
In order to sketch, why steganography is such an important topic, and has received far too little attention from the hacker community in the past, let me quickly challenge our view of cryptosystems as commonly built in the context of military or commercial applications: Cryptosystems are designed to protect our sensitive data from evil arbitrators....
This report provides an overview of the core problems of natural language processing, discussing the issues of morphology, syntax and semantics and presenting the techniques that are most commonly used to address them. Each of these aspects is first elaborated on from a linguistic point of view, then the problem is simplified and idealized, and fin...
Steganographic systems provide a secure medium to covertly transmit information in the presence of an arbitrator. In linguistic steganography, in particular, machine-readable data is to be encoded to innocuous natural language text, thereby providing security against any arbitrator tolerating natural language as a communication medium.
So far, the...
Abstract In the present report we give a thorough exposition of our first steps towards a theory of fuzzy semantics and towards the development of a closed domain question answering system in the form of a natural language database interface that produces result sets ranked according to the degree to which they fulfill our intuitions about vague ex...