All in-text references underlined in blue are linked to publications on ResearchGate, letting you... more All in-text references underlined in blue are linked to publications on ResearchGate, letting you access and read them immediately.
Proceedings of the 3rd International Workshop on Data Science for Macro--Modeling with Financial and Economic Datasets, 2017
In this paper we describe a machine learning approach to predict roles of extracted SEC triples f... more In this paper we describe a machine learning approach to predict roles of extracted SEC triples for the non-scored task of the 2017 FEIII Challenge. In addition, we describe a graph and data analysis derived from SEC triples.
L'invention concerne un procede de production d'un rapport a partir de plusieurs sources,... more L'invention concerne un procede de production d'un rapport a partir de plusieurs sources, qui consiste a: obtenir un sujet base sur des requetes d'entree se rapportant au sujet; obtenir sur le sujet, a partir de la multitude de sources, des informations comprenant des extraits respectant un ou plusieurs criteres; et exploiter ces extraits pour produire le rapport. La production du rapport consiste a: obtenir des sous-sujets pour les extraits; utiliser les sous-sujets pour organiser les extraits; et modifier le texte contenu dans les extraits.
2008 11th International Conference on Information Fusion, 2008
Enemy Courses of Action (ECOAs) play a central role in the process of situation development in mi... more Enemy Courses of Action (ECOAs) play a central role in the process of situation development in military decision-making. In order to reason about ECOAs, it would be necessary to adequately represent them in a formalism that allows for automatic reasoning. In this paper, we examine the benefits and drawbacks of representing ECOAs within several frameworks that have been encoded as OWL ontologies.
: The Problem Statement for this briefing addresses the following issues: *Information about Enem... more : The Problem Statement for this briefing addresses the following issues: *Information about Enemy Courses of Action (ECOAs) must be shared by coalition forces. *Potentially, a shared representational language for describing ECOAs is needed that can be used with C4 systems. *The standard exchange language for sharing such information among NATO forces today is the Joint Command, Control, and Consultation Information Exchange Data Mode (JC3IEDM). *In this paper we explore the formal representational requirements for describing ECOAs and evaluate the effectiveness of JC3IEDM for this purpose. *In previous work, we have automatically translated JC3IEDM into OWL (a computationally tractable W3C logical representation that supports ontological reasoning). Aim is to investigate potential for reasoning about ECOAs automatically in C4 systems. Associated with each ECOA, there is (are): *Situation template which normally consists of a Modified Combined Obstacle Overlay, depicting the operati...
In this paper, we describe a system that semantically annotates streams of reports about transnat... more In this paper, we describe a system that semantically annotates streams of reports about transnational criminal gangs in order to automatically produce models of the gangs' membership and activities in the form of a semantic wiki. A gang ontology and semantic inferencing are used to annotate the reports and supplement entity and relationship annotations based on the local document context. Reports in the datastream are annotated for reliability and credibility in the proof-of-concept system.
As the leading source of intelligent information, Thomson Reuters delivers must-have insight to t... more As the leading source of intelligent information, Thomson Reuters delivers must-have insight to the world’s financial and risk, legal, tax and accounting, intellectual property, science and media professionals, supported by the world's most trusted news organization. In this paper we describe a recent initiative at Thomson Reuters to establish Big Data infrastructure to store most of this data, and to apply open standards for linking the contents of this data. We describe our wish list of technology not currently available from open source and commercial solutions for a next generation big document and data system.
: Commanders require relevant information about background information in order to exercise effec... more : Commanders require relevant information about background information in order to exercise effective command and control (C2). METT-TC factors (Mission, Enemy, Terrain & Weather, Troops, Time Available and Civil Considerations) represent the canonical, militarily significant background against which information is evaluated and military decisions are made. If this background is to be encoded, shared, and, ultimately, processed and reasoned about by computers or computer-assisted C2 systems, the METT-TC background must be represented in some standard format with a shared computer-processable semantics. The JC3IEDM (Joint Command, Control, and Consultation Information Exchange Data Model) represents several years of effort by NATO's Multinational Interoperability Programme at developing a representation of military situations in order to support communication and interoperability among NATO forces. All information to be shared by participants must, therefore, be representable wit...
: Doctrinally, Priority Intelligence Requirements (PIRs) are information that the commander needs... more : Doctrinally, Priority Intelligence Requirements (PIRs) are information that the commander needs to know in order to make a decision or achieve a desired effect. Networked warfare provides the intelligence officer with access to multitudes of reports and sensor outputs. What technology can the intelligence officer use to find answers to PIRs in this sea of information? Recent developments in enterprise search technology have accelerated. To what extent can commercial search technologies assist with the task of PIR answering? In this paper, we outline doctrinal approaches to PIRs and PIR answering and explore how they have been adapted to contemporary warfare. We then explore five types of question-answering technologies: structured data technologies; unstructured textbased technologies; semistructured or "tagged text'-based logic or "semantic web" technologies; and social question-answering technologies. We identify gaps in the PIR answering process that cannot b...
The amount of RDF data available on the Web has been increasingly growing over the past few years... more The amount of RDF data available on the Web has been increasingly growing over the past few years. Developing and fine-tuning SPARQL queries in order to sift through the data may be a very challenging task for human operators who need to quickly make sense of large graphs. In addition, often multiple queries need to be issued in order to gather and understand the context (relevant facts) for the explanation of the query. Thus, the challenge is not only to answer the query, but also to provide context, so that the analyst can easily comprehend what the data is actually conveying. This paper describes results of an investigation of the possibility to apply key aspects of Situation Theory, and its ontological realization in the Situation Theory Ontology, to simplify and abstract large RDF data sets, given a focus query from the analyst. In this approach, the query results are presented as concept maps. The approach was successfully implemented as a prototype, although this paper does n...
In this report, we investigate the relationship between the semantic and syntactic properties of ... more In this report, we investigate the relationship between the semantic and syntactic properties of verbs. Our work is based on the English Verb Classes and Alternations of (Levin, 1993). We explore how these classes are manifested in other languages, in particular, in Bangla, German, and Korean. Our report includes a survey and classi cation of several hundred verbs from these languages into the cross-linguistic equivalents of Levin's classes. We also explore ways in which our ndings may be used to enhance WordNet in two ways: making the English syntactic information of WordNet more ne-grained, and making WordNet multilingual. Copyright c Massachusetts Institute of Technology, 1994 This report describes research done at the Arti cial Intelligence Laboratory of the Massachusetts Institute of Technology. This research is supported by NSF grant 9217041-ASC and ARPA under the HPCC program, as well as by a generous grant from the NEC Corporation.
All in-text references underlined in blue are linked to publications on ResearchGate, letting you... more All in-text references underlined in blue are linked to publications on ResearchGate, letting you access and read them immediately.
Proceedings of the 3rd International Workshop on Data Science for Macro--Modeling with Financial and Economic Datasets, 2017
In this paper we describe a machine learning approach to predict roles of extracted SEC triples f... more In this paper we describe a machine learning approach to predict roles of extracted SEC triples for the non-scored task of the 2017 FEIII Challenge. In addition, we describe a graph and data analysis derived from SEC triples.
L'invention concerne un procede de production d'un rapport a partir de plusieurs sources,... more L'invention concerne un procede de production d'un rapport a partir de plusieurs sources, qui consiste a: obtenir un sujet base sur des requetes d'entree se rapportant au sujet; obtenir sur le sujet, a partir de la multitude de sources, des informations comprenant des extraits respectant un ou plusieurs criteres; et exploiter ces extraits pour produire le rapport. La production du rapport consiste a: obtenir des sous-sujets pour les extraits; utiliser les sous-sujets pour organiser les extraits; et modifier le texte contenu dans les extraits.
2008 11th International Conference on Information Fusion, 2008
Enemy Courses of Action (ECOAs) play a central role in the process of situation development in mi... more Enemy Courses of Action (ECOAs) play a central role in the process of situation development in military decision-making. In order to reason about ECOAs, it would be necessary to adequately represent them in a formalism that allows for automatic reasoning. In this paper, we examine the benefits and drawbacks of representing ECOAs within several frameworks that have been encoded as OWL ontologies.
: The Problem Statement for this briefing addresses the following issues: *Information about Enem... more : The Problem Statement for this briefing addresses the following issues: *Information about Enemy Courses of Action (ECOAs) must be shared by coalition forces. *Potentially, a shared representational language for describing ECOAs is needed that can be used with C4 systems. *The standard exchange language for sharing such information among NATO forces today is the Joint Command, Control, and Consultation Information Exchange Data Mode (JC3IEDM). *In this paper we explore the formal representational requirements for describing ECOAs and evaluate the effectiveness of JC3IEDM for this purpose. *In previous work, we have automatically translated JC3IEDM into OWL (a computationally tractable W3C logical representation that supports ontological reasoning). Aim is to investigate potential for reasoning about ECOAs automatically in C4 systems. Associated with each ECOA, there is (are): *Situation template which normally consists of a Modified Combined Obstacle Overlay, depicting the operati...
In this paper, we describe a system that semantically annotates streams of reports about transnat... more In this paper, we describe a system that semantically annotates streams of reports about transnational criminal gangs in order to automatically produce models of the gangs' membership and activities in the form of a semantic wiki. A gang ontology and semantic inferencing are used to annotate the reports and supplement entity and relationship annotations based on the local document context. Reports in the datastream are annotated for reliability and credibility in the proof-of-concept system.
As the leading source of intelligent information, Thomson Reuters delivers must-have insight to t... more As the leading source of intelligent information, Thomson Reuters delivers must-have insight to the world’s financial and risk, legal, tax and accounting, intellectual property, science and media professionals, supported by the world's most trusted news organization. In this paper we describe a recent initiative at Thomson Reuters to establish Big Data infrastructure to store most of this data, and to apply open standards for linking the contents of this data. We describe our wish list of technology not currently available from open source and commercial solutions for a next generation big document and data system.
: Commanders require relevant information about background information in order to exercise effec... more : Commanders require relevant information about background information in order to exercise effective command and control (C2). METT-TC factors (Mission, Enemy, Terrain & Weather, Troops, Time Available and Civil Considerations) represent the canonical, militarily significant background against which information is evaluated and military decisions are made. If this background is to be encoded, shared, and, ultimately, processed and reasoned about by computers or computer-assisted C2 systems, the METT-TC background must be represented in some standard format with a shared computer-processable semantics. The JC3IEDM (Joint Command, Control, and Consultation Information Exchange Data Model) represents several years of effort by NATO's Multinational Interoperability Programme at developing a representation of military situations in order to support communication and interoperability among NATO forces. All information to be shared by participants must, therefore, be representable wit...
: Doctrinally, Priority Intelligence Requirements (PIRs) are information that the commander needs... more : Doctrinally, Priority Intelligence Requirements (PIRs) are information that the commander needs to know in order to make a decision or achieve a desired effect. Networked warfare provides the intelligence officer with access to multitudes of reports and sensor outputs. What technology can the intelligence officer use to find answers to PIRs in this sea of information? Recent developments in enterprise search technology have accelerated. To what extent can commercial search technologies assist with the task of PIR answering? In this paper, we outline doctrinal approaches to PIRs and PIR answering and explore how they have been adapted to contemporary warfare. We then explore five types of question-answering technologies: structured data technologies; unstructured textbased technologies; semistructured or "tagged text'-based logic or "semantic web" technologies; and social question-answering technologies. We identify gaps in the PIR answering process that cannot b...
The amount of RDF data available on the Web has been increasingly growing over the past few years... more The amount of RDF data available on the Web has been increasingly growing over the past few years. Developing and fine-tuning SPARQL queries in order to sift through the data may be a very challenging task for human operators who need to quickly make sense of large graphs. In addition, often multiple queries need to be issued in order to gather and understand the context (relevant facts) for the explanation of the query. Thus, the challenge is not only to answer the query, but also to provide context, so that the analyst can easily comprehend what the data is actually conveying. This paper describes results of an investigation of the possibility to apply key aspects of Situation Theory, and its ontological realization in the Situation Theory Ontology, to simplify and abstract large RDF data sets, given a focus query from the analyst. In this approach, the query results are presented as concept maps. The approach was successfully implemented as a prototype, although this paper does n...
In this report, we investigate the relationship between the semantic and syntactic properties of ... more In this report, we investigate the relationship between the semantic and syntactic properties of verbs. Our work is based on the English Verb Classes and Alternations of (Levin, 1993). We explore how these classes are manifested in other languages, in particular, in Bangla, German, and Korean. Our report includes a survey and classi cation of several hundred verbs from these languages into the cross-linguistic equivalents of Levin's classes. We also explore ways in which our ndings may be used to enhance WordNet in two ways: making the English syntactic information of WordNet more ne-grained, and making WordNet multilingual. Copyright c Massachusetts Institute of Technology, 1994 This report describes research done at the Arti cial Intelligence Laboratory of the Massachusetts Institute of Technology. This research is supported by NSF grant 9217041-ASC and ARPA under the HPCC program, as well as by a generous grant from the NEC Corporation.
Uploads
Papers by Brian Ulicny