arXiv subjects

Michael Wessel

Publications and source records attributed to Michael Wessel.

5 recordsLinked to original sources

arXiv2026

A Virtual Member of a Community of Practice for the Society of Petroleum Engineers: From Prototype to Deployment

We describe the evolution of a virtual assistant, called ATHENA, designed to support the capture, retrieval, and dissemination of knowledge for members of a Community of Practice (CoP) related to the Oil and Gas sector. An evaluation of a first prototype involving 75 professionals from the Society of Petroleum Engineering (SPE) showed that ATHENA dramatically improved both their productivity and performance equality on a set of realistic well-planning tasks compare to their use of a state-of-the-art RAG baseline system. However, the evaluation also identified areas for improvement. This paper describes technical advances to our first prototype in the areas of multi-document retrieval, support for answer validation, and more focused proactive dissemination. Evaluation results show that this enhanced version of ATHENA provides better support for completing knowledge-intensive tasks related to well planning than does a state-of-the-art baseline. ATHENA has been integrated into the SPE Research Portal and is being deployed for use by the society's membership.

cs.CL↗

arXiv2023

Notes on Refactoring Exponential Macros in Common Lisp

I recently consulted for a very big Common Lisp project having more than one million lines of code (including comments). Let's call it "System X" in the following. System X suffered from extremely long compilation times; i.e., a full recompile took about 33:17 minutes on a 3.1 GHz MacBook Pro Intel Core i7 with SSD and 16 GBs of RAM, using ACL 10.1. It turns out that a number of macros were causing an exponential code blowup. With these macros refactored, the system then recompiled in 5:30 minutes - a speedup by a factor of ~ 6. In this experience report, I will first illuminate the problem, and then demonstrate two potential solutions in terms of macro refactoring techniques. These techniques can be applied in related scenarios.

cs.PL↗

arXiv2020

Widening the Dialogue Workflow Modeling Bottleneck in Ontology-Based Personal Assistants

We present a new approach to dialogue specification for Virtual Personal Assistants (VPAs) based on so-called dialogue workflow graphs, with several demonstrated advantages over current ontology-based methods. Our new dialogue specification language (DSL) enables customers to more easily participate in the VPA modeling process due to a user-friendly modeling framework. Resulting models are also significantly more compact. VPAs can be developed much more rapidly. The DSL is a new modeling layer on top of our ontology-based Dialogue Management (DM) framework OntoVPA. We explain the rationale and benefits behind the new language and support our claims with concrete reduced Level-of-Effort (LOE) numbers from two recent OntoVPA projects.

cs.CL↗

arXiv2015

Charging of Cu atom on Mo supported thin films of ScN, MgO and NaF

Molybdenum supported thin films of ScN, MgO and NaF with a Cu adatom have been studied in the framework of density functional theory. We have observed a charge transfer from the metal/film interface to the Cu atom and investigated its relation to surface and interface deformations. We find that a weak interaction between the metal and the film is a promising prerequisite for adatom charging. The detailed study of Cu/NaF/Mo and NaF/Mo indicates that the distortion of the NaF film caused by the Cu adsorption has essentially anharmonic character, as it is coupled to a strong charge redistribution in the system.

cond-mat.mtrl-sci↗

arXiv2013

Query Answering in Object Oriented Knowledge Bases in Logic Programming: Description and Challenge for ASP

Research on developing efficient and scalable ASP solvers can substantially benefit by the availability of data sets to experiment with. KB_Bio_101 contains knowledge from a biology textbook, has been developed as part of Project Halo, and has recently become available for research use. KB_Bio_101 is one of the largest KBs available in ASP and the reasoning with it is undecidable in general. We give a description of this KB and ASP programs for a suite of queries that have been of practical interest. We explain why these queries pose significant practical challenges for the current ASP solvers.

cs.AI↗