Peter Clark

44. Interpreting and Reasoning with Simple Natural Language Sentences

2014 A discussion on how generic sentences can be interpreted and reasoned with.

43. Project Halo: Making Sense of Questions in a Knowledge-Rich Environment

2011 Invited presentation at the DARPA Machine Reading Year Three Kickoff Meeting.

42. Creating BLUE Formulations of the Refinement Phase Test Suite (RTS) Questions: Experience and Reflections

2010 We spent three months adding biology and lexical knowledge so that AURA could answer a test suite of fluently worded English questions. This document summarizes this experience, and its implications for future QA work with AURA.

41. Query Relaxation in AURA

2010 An intermediate reflection on the possible roles of query relaxation in AURA's QA module.

40. A Brief Overview of Some Datapoints in the Query Relaxation Literature

2009 A short literature survey of the main themes in this area in the database literature.

39. RTE5: An Informal Analysis of Some Interesting Textual Entailment Examples

2010 A fairly informal discussion of what it would take to infer a hypothesis H from a text T for some selected RTE5 examples, using lexical and world knowledge (as opposed to shallow, statistical matching techniques).

38. The KM to SILK Translator - Preliminary Design and Implementation

2010 A technical discussion of how to convert KM's prototypes, as build by knowledge engineers using the AURA system, into the F-Logic-like language SILK. Examples Used in Working Note PowerPoint Overview Lisp Implementation

37. Evaluation of the New Paraphrase and Question Formulation Capability in AURA

2010 A description of recent developments in AURA's question-answering capabilities.

36. The Semantics of Questions

2010 A discussion of the formal semantics of some of the questions posed to AURA, with particular focus on the relationship between universals and hypotheticals.

35. BLUE (Boeing Language Understanding Engine): A Quick Tutorial on How it Works

2009 A short and sweet PowerPoint summary Also see the technical paper Boeing's NLP System and the Challenges of Semantic Representation, for longer discussion and illustrations

34.On the Relation between "Semantically Tractable" Queries and AURA's Question Formulation Facility

2009 A discussion of Popescu et al's notion of "semantically tractable" questions in natural language interfaces to databases, and the extent to which it can be applied to asking questions in the AURA system.

33. A Study of Some "Hard to Formulate" Biology Questions

2009 An analysis of 22 biology questions that the users had trouble expressing in our controlled language CPL in the AURA system.

32. Why is it Hard to Understand Original English Questions?

2009 The AURA knowledge-based system currently requires users to reformulate questions in a simplified version of English called CPL. This document discusses some of the obstacles to having AURA understand the original English questions directly.

31. On the Relationship of AURA Question-Answering and Textual Entailment

2009 How question-answering in a textbook-derived knowledge-based system and the Recognizing Textual Entailment (RTE) challenge are closely related.

30. Using Scripts to help in Biomedical Text Interpretation

2009 A worked example of how general knowledge of transportation can be used to guide interpretation of biomedical text.

29. The Problem of Unrealized Complements and its Relation to Frames and Scripts

2008 A short discussion of the issues in, and solutions to, the problem of "missing" (unstated) elements in text.

28. Do Scripts Solve NLP?

2008 A discussion on the use of scripts to understand the MUC-3 kidnapping articles.

27. Representing "improvement": A Short Study on an RTE Example

2007 A discussion on how to represent the notion of "improve" and "better", set in the context of language processing (textual entailment).

26. Making Sense of Sentences

2001 ome examples of trying to align variations of an input sentence with background knowledge.

25. Reference Resolution and Views

2001 How background knowledge might be used to resolve indirect references in text.

24. From Natural Language to KM Representations

2001 Some extremely preliminary thoughts. The toy demo code is also available here.

23. Concept Variation and Example Generation: Some Preliminary Thoughts

2001 This little working note presents some brief thoughts on handling variation among members of a concept, and generating examples of that concept.

22. More Thoughts on Views

2001 Some further, assorted thoughts on the notion of `views' in a KB. Co-authored with John Thompson and the UT KB group.

21. A Proposal for a Process Specification Language

2001 Co-authored with John Thompson. Presents some key concepts and examples for representing processes and their executions in KM.

20. Understanding Role Concepts

2000 This note gives a new discussion of role concepts, superceding the earlier (and in places erroneous) Working Note number 11. This working note is currently being revised and will appear shortly.

19. Using Views in a Knowledge Base

2000 Discusses the notion of "views", namely explicit representations of how general concepts can be applied to more domain-specific concepts. Co-authored with John Thompson, Ken Barker, James Fan, Bruce Porter, Dan Tecuci, Peter Yeh.

18. Constructing Scripts Compositionally: A Molecular Biology Example

2000 This note follows on from Working Note 17, to provide another example (with less discussion), this one from the molecular biology domain about how a virus works. KM KBs: Classes, Prototypes Graphlet Database

17. $RESTAURANT re-visited: A KM Implementation of a Compositional Approach

2000 A worked KM example of a familiar AI problem. This paper also compares class-based and prototype-based styles in KM. KM KBs: Classes, Prototypes Graphlet Database

16. Translating from CCALC into KM: An Example

1999 Comparison of two representation languages, CCALC and KM, for a simple problem. Co-authored with Joohyung Lee, Vladimir Lifschitz, and Bruce Porter.

15. From Text to Paragraph Representations

1999 A discussion of the gap between NLP-generated semantic graphs, and a fuller representation of meaning, for a short paragraph of text.

14. Story Generation and Aviation Incident Representation

1999 Discusses the representation and generation of aviation incident 'stories'. Prolog Code

13. Knowledge Patterns

1998 A discussion of components as theory 'patterns' or 'templates', which get instantiated ('morphed') in various ways for reasoning.

12. More on Components

1998 A more detailed discussion of component data-structures and composition.

11. Should Role Concepts be Included in a Taxonomy?

1998 A brief discussion of how to place `role concepts' (eg. Teacher, Producer) in a taxonomy.

10. Requirements for a Knowledge Representation System

1996 An attempt to enumerate general requirements for a KR system, with some example representational challenges.

9. Representing Conceptual Graphs in Algernon

1996 A discussion of conceptual graphs, and how they might be represented in the KR language Algernon.

8. The Help-Desk Assistant Project

1996 A pictorial overview of the DCE Help-Desk Project. (0.8MB compressed, uncompresses to 26MB due to color images).

7. Object Descriptions Revisited

1995 A view of components as a self-contained system of relationships, with a clearer delineation. Also see the AAAI'97 paper for the evolution of this theme.

6. Constructing Scripts from Components

1995 Describes representing stereotypical action sequences (`scripts') compositionally, employing ideas from Batory's GenVoca approach to software composition.

5. KI Revisited

1995 An overview and discussion of Ken Murray's KI system for Knowledge Integration.

4. Building Action Descriptions from Components

1995 Describes representing STRIPS-style actions compositionally.

3. Concept Construction as Constraint Relaxation

1995 Thoughts on dealing with contradictions between components during composition. LIFE Code

2. Components and Contexts

1995 An exporation of connections between the idea of components, contexts, composition, and problem-solving.

1. Building Concepts from Components

1994 Initial thoughts on representations as compositions, visualized as graph superposition.

Peter Clark

Senior Research Manager