Arrow Research search

Author name cluster

Mark Burstein

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers
1 author row

Possible papers

6

JAAMAS Journal 2026 Journal Article

Derivation of Glue Code for Agent Interoperation

  • Mark Burstein
  • Drew McDermott
  • STEPHEN J. WESTFOLD

Abstract Getting agents to communicate requires translating the data structures of the sender (the source representation) to the format required by the receiver (the target representation). Assuming that there is a formal theory of the semantics of the two formats, which explains both their meanings in terms of a neutral topic domain, we can cast the translation problem as solving higher-order functional equations. Some simple rules and strategies apparently suffice to solve these equations automatically. The strategies may be summarized as: decompose complex expressions, replacing topic-domain expressions with source-domain expressions when necessary. A crucial issue is getting the required formal theories of the source and target domains. We believe it is sufficient to find partial formalizations that grow as necessary.

Details DOI

AAAI Conference 2017 System Paper

Natural Language Dialogue for Building and Learning Models and Structures

  • Ian Perera
  • James Allen
  • Lucian Galescu
  • Choh Man Teng
  • Mark Burstein
  • Scott Friedman
  • David McDonald
  • Jeffrey Rye

We demonstrate an integrated system for building and learning models and structures in both a real and virtual environment. The system combines natural language understanding, planning, and methods for composition of basic concepts into more complicated concepts. The user and the system interact via natural language to jointly plan and execute tasks involving building structures, with clarifications and demonstrations to teach the system along the way. We use the same architecture for building and simulating models of biology, demonstrating the general-purpose nature of the system where domain-specific knowledge is concentrated in sub-modules with the basic interaction remaining domain-independent. These capabilities are supported by our work on semantic parsing, which generates knowledge structures to be grounded in a physical representation, and composed with existing knowledge to create a dynamic plan for completing goals. Prior work on learning from natural language demonstrations enables learning of models from very few demonstrations, and features are extracted from definitions in natural language. We believe this architecture for interaction opens up a wide possibility of human-computer interaction and knowledge transfer through natural language.

PDF Details

IJCAI Conference 2009 Conference Paper

  • Fusun Yaman
  • Tim Oates
  • Mark Burstein

Existing work on workflow mining ignores the dataflow aspect of the problem. This is not acceptable for service-oriented applications that use Web services with typed inputs and outputs. We propose a novel algorithm WIT (Workflow Inference from Traces) which identifies the context similarities of the observed actions based on the dataflow and uses model merging techniques to generalize the control flow and the dataflow simultaneously. We identify the class of workflows that WIT can learn correctly. We implemented WIT and tested it on a real world medical scheduling domain where WIT was able to find a good approximation of the target workflow.

PDF Details

AAAI Conference 2008 Conference Paper

POIROT — Integrated Learning of Web Service Procedures

  • Mark Burstein
  • David McDonald
  • Brett Benyo
  • Talib Hussain

POIROT is an integration framework for combining machine learning mechanisms to learn hierarchical models of web services procedures from a single or very small set of demonstration examples. The system is organized around a shared representation language for communications with a central hypothesis blackboard. Component learning systems share semantic representations of their hypotheses (generalizations) and inferences about demonstration traces. To further the process, components may generate learning goals for other learning components. POIROT’s learners or hypothesis formers develop workflows that include order dependencies, subgoals, and decision criteria for selecting or prioritizing subtasks and service parameters. Hypothesis evaluators, guided by POIROT’s meta-control component, plan experiments to confirm or disconfirm hypotheses extracted from these learning products. Collectively, they create methods that POIROT can use to reproduce the demonstration and solve similar problems. After its first phase of development, POIROT has demonstrated it can learn some moderately complex hierarchical task models from semantic traces of user-generated service transaction sequences at a level that is approaching human performance on the same learning task.

PDF Details
v2026.09.13