Skip to main content

Inderjeet Mani

Followers

179

Following

4

Co-authors

2

Public Views

Carnegie Mellon University

SUNY: University at Buffalo

Universidade de Évora

Philosophisch-Theologische Hochschule Brixen

University at Buffalo, State University of New York

Albert-Ludwigs-University of Freiburg

Royal Society of Chemistry

Interests

Uploads

Papers by Inderjeet Mani

The Evaluation of Ontologies

Semantic Web, 2007

Recent years have seen rapid progress in the development of ontologies as semantic models intende... more Recent years have seen rapid progress in the development of ontologies as semantic models intended to capture and represent aspects of the real world. There is, however, great variation in the quality of ontologies. If ontologies are to become progressively better in the future, more rigorously developed, and more appropriately compared, then a systematic discipline of ontology evaluation must be created to ensure quality of content and methodology. Systematic methods for ontology evaluation will take into account representation of individual ontologies, performance (in terms of accuracy, domain coverage and the efficiency and quality of automated reasoning using the ontologies) on tasks for which the ontology is designed and used, degree of alignment with other ontologies and their compatibility with automated reasoning. A sound and systematic approach to ontology evaluation is required to transform ontology engineering into a true scientific and engineering discipline. This chapter discusses issues and problems in ontology evaluation, describes some current strategies, and suggests some approaches that might be useful in the future.

TIME 2010 Committees

computer.org

General Chair Ian Pratt-Hartmann, University of Manchester, UK ... Program Committee Chairs Nicol... more General Chair Ian Pratt-Hartmann, University of Manchester, UK ... Program Committee Chairs Nicolas Markey, CNRS & ENS Cachan, France Jef Wijsen, University of Mons, Belgium ... Organization Chair Nicolas Markey, CNRS & ENS Cachan, France ... Program Committee Alessandro Artale, Free University of Bozen-Bolzano, Italy Howard Barringer, University of Manchester, UK Béatrice Bérard, University Paris 6-Pierre & Marie Curie, France Claudio Bettini, University of Milan, Italy Davide Bresolin, University of Verona, Italy Thomas Brihaye, University of ...

The Computational Treatment of Nominals

Additional copies of these proceedings may be ordered while stocks last from: Association for Com... more Additional copies of these proceedings may be ordered while stocks last from: Association for Computational Lingustics (ACL) 75 Paterson Street, Suite 9 New Brunswick, NJ 08901 USA Tel: +1-732-342-9100 Fax: +1-732-873-0014 rasmusse© cs. rutger s. edu ... ORGANIZING COMMITTEE: Federica Busa (Brandeis University) Inderjeet Mani (The MITRE Corporation) Patrick Saint-Dizier (IRIT, Universit~ Paul Sabatier) ... PROGRAM COMMITTEE: Federica Busa (Brandeis University) Mark Gawron (SRI International) Bob Ingria (Psyche Systems Corporation) ...

Narrative summarization: Résumé automatique de textes

TAL. Traitement automatique des langues, 2004

Résumé/Abstract La compréhension et le résumé automatique de la narration sont difficiles, en rai... more Résumé/Abstract La compréhension et le résumé automatique de la narration sont difficiles, en raison de l'incapacité des systèmes automatiques d'identfier le vrai contenu de l'information. Ceci peut avoir comme conséquence le choix inadéquat du contenu aussi bien que l'incohérence du résumé. Cet article présente une nouvelle conception pour le résumé automatique de la narration, qui repose sur l'exploitation d'information temporelle. Cette conception distingue trois niveaux: scène, histoire et intrigue. L'article décrit comment ...

Introduction to the special issue on temporal information processing

ACM Transactions on Asian Language Information Processing, 2004

Time is a key dimension of our information space, with many applications standing to benefit from... more Time is a key dimension of our information space, with many applications standing to benefit from exploiting it. This special issue is devoted to temporal information processing for natural language as well as temporal reasoning. We begin by describing some of the ways time is expressed in natural language, and the particular requirements this imposes on information processing systems. We then provide an overview of current annotation-based approaches to temporal information extraction, followed by an introduction to the relevant literature on temporal reasoning. We also provide brief synopses of the articles in this issue, situating them in a broader context. We end with administrative remarks about the creation of this special issue.

Predicting Reader Response in Narrative

This paper sketches a theory of how readers (or users, or players, or viewers) respond to narrati... more This paper sketches a theory of how readers (or users, or players, or viewers) respond to narratives. Such a theory can be useful for developing evaluation functions to allow for narrative outcomes that have maximum impact at particular times on the reader. The reader's response is viewed in terms of character evaluations, namely judgments of sympathy or antipathy for the agent involved in that outcome. Character development is computed in terms of transitions in reader evaluations for an agent over the time course of the narrative. To formally model character evaluations, we begin with a representation of the narrative fabula in terms of the events, their participant roles, and their temporal relations. This representation is implemented on a corpus of narratives with existing tools and standards. Reader evaluations are annotated on events in the fabula. Once high reliability in human character evaluations has been proven, a character evaluation tagger will be trained on these evaluations.

Annotation of Temporal Relations with Tango

Temporal annotation is a complex task characterized by low markup speed and low inter-annotator a... more Temporal annotation is a complex task characterized by low markup speed and low inter-annotator agreements scores. Tango is a graphical annotation tool for temporal relations. It is developed for the TimeML annotation language and allows annotators to build a graph that resembles a timeline. Temporal relations are added by selecting events and drawing labeled arrows between them. Tango is integrated

Guidelines for annotating temporal information

Human Language Technology, 2000

This paper introduces a set of guidelines for annotating time expressions with a canonicalized re... more This paper introduces a set of guidelines for annotating time expressions with a canonicalized representation of the times they refer to. Applications that can benefit from such an annotated corpus include information extraction (e.g., normalizing temporal references for database entry), question answering (answering "when" questions), summarization (temporally ordering information), machine translation (translating and normalizing temporal references), and information visualization (viewing

Summarization Evaluation: An Overview

North American Chapter of the Association for Computational Linguistics, 2001

This paper provides an overview of different meth- ods for evaluating automatic summarization sys... more This paper provides an overview of different meth- ods for evaluating automatic summarization systems. The challenges in evaluating summaries are charac- terized. Both intrinsic and extrinsic approaches are discussed. Methods for assessing informativeness and coherence are described. The advantages and disad- vantages of specific methods are assessed, along with criteria for choosing among them. The paper con- cludes with some

Towards content-based browsing of broadcast news video

Multimedia Information Retrieval, 1997

... Published in: · Book. Intelligent multimedia information retrieval. MIT Press Cambridge, MA, ... more

Producing Biographical Summaries: Combining Linguistic Knowledge with Corpus Statistics

Meeting of the Association for Computational Linguistics, 2001

We describe a biographical multi-document summarizer that summarizes information about people des... more We describe a biographical multi-document summarizer that summarizes information about people described in the news. The summarizer uses corpus statistics along with linguistic knowledge to select and merge descriptions of people from a document collection, removing redundant descriptions. The summarization components have been extensively evaluated for coherence, accuracy, and non-redundancy of the descriptions produced.

The TIPSTER SUMMAC Text Summarization Evaluation

The,TIPSTER Text,Summarization Evaluation (SUMMAC) has established definitively that automatic,te... more The,TIPSTER Text,Summarization Evaluation (SUMMAC) has established definitively that automatic,text summarization is very effective in relevance assessment,tasks. Summaries,as short as 17% of full text length sped up decisionmaking,by almost,a factor of 2 with no statistically significant degradation,in Fscore accuracy. SUMMAC has also introduced,a new intrinsic method,for automated,evaluation of informative,summaries.

Improving Summaries by Revising Them

Meeting of the Association for Computational Linguistics, 1999

This paper describes a program which revises a draft text by aggregating together descriptions of... more This paper describes a program which revises a draft text by aggregating together descriptions of discourse entities, in addition to deleting ex- traneous information. In contrast to knowledge- rich sentence aggregation approaches explored in the past, this approach exploits statistical parsing and robust coreference detection. In an evaluation involving revision of topic-related summaries using informativeness measures from the TIPSTER SUMMAC

A Multilingual Approach to Annotating and Extracting Temporal Information1

Meeting of the Association for Computational Linguistics, 2000

This paper introduces a set of guidelines for annotating time expressions with a canonicalized re... more

The tipster summac text summarization evaluation final report

The TIPSTER Text Summarization Evaluation (SUMMAC) has established definitively that automatic te... more The TIPSTER Text Summarization Evaluation (SUMMAC) has established definitively that automatic text summarization is very effective in relevance assessment tasks. Summaries as short as 17% of full text length sped up decisionmaking by almost a factor of 2 with no statistically significant degradation in Fscore accuracy. SUMMAC has also introduced a new intrinsic method for automated evaluation of informative summaries.

Summarizing Similarities and Differences Among Related Documents

Information Retrieval, 1999

In many modern information retrieval applications, a common problem which arises is the existence... more In many modern information retrieval applications, a common problem which arises is the existence of multiple documents covering similar information, as in the case of multiple news stories about an event or a sequence of events. A particular challenge for text summarization is to be able to summarize the similarities and differences in information content among these documents. The approach described here exploits the results of recent progress in information extraction to represent salient units of text and their relationships. By exploiting meaningful relations between units based on an analysis of text cohesion and the context in which the comparison is desired, the summarizer can pinpoint similarities and differences, and align text segments. In evaluation experiments, these techniques for exploiting cohesion relations result in summaries which (i) help users more quickly complete a retrieval task (ii) result in improved alignment accuracy over baselines, and (iii) improve identification of topic-relevant similarities and differences.

Multi-Document Summarization by Graph Search and Matching

Computing Research Repository, 1997

We describe a new method for summarizing similar- ities and dierences in a pair of related docume... more We describe a new method for summarizing similar- ities and dierences in a pair of related documents using a graph representation for text. Concepts de- noted by words, phrases, and proper names in the document are represented positionally as nodes in the graph along with edges corresponding to semantic re- lations between items. Given a perspective in terms of which

Inferring temporal ordering of events in news

Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology companion volume of the Proceedings of HLT-NAACL 2003--short papers - NAACL '03, 2003

This paper describes a domain-independent, machine-learning based approach to temporally anchorin... more

A pilot study on acquiring metric temporal constraints for events

Proceedings of the Workshop on Annotating and Reasoning about Time and Events - ARTE '06, 2006

Previous research on temporal anchoring and ordering has focused on the annotation and learning o... more Previous research on temporal anchoring and ordering has focused on the annotation and learning of temporal relations between events. These qualitative relations can be usefully supplemented with information about metric constraints, specifically as to how long events last. This paper describes the first steps in acquiring metric temporal constraints for events. The work is carried out in the context of the TimeML framework for marking up events and their temporal relations. This pilot study examines the feasibility of acquisition of metric temporal constraints from corpora.

Recent developments in temporal information extraction

Current Issues in Linguistic Theory, 2004

The growing interest in practical NLP applications such as text summarization and question-answer... more The growing interest in practical NLP applications such as text summarization and question-answering places increasing demands on the processing of temporal information in natural languages. To support this, several new capabilities have emerged. These include the ability to tag events and time expressions, to temporally anchor and order events, and to build models of the temporal structure of discourse. This paper describes some of the techniques and the further challenges that arise.

The Evaluation of Ontologies

Semantic Web, 2007

Recent years have seen rapid progress in the development of ontologies as semantic models intende... more Recent years have seen rapid progress in the development of ontologies as semantic models intended to capture and represent aspects of the real world. There is, however, great variation in the quality of ontologies. If ontologies are to become progressively better in the future, more rigorously developed, and more appropriately compared, then a systematic discipline of ontology evaluation must be created to ensure quality of content and methodology. Systematic methods for ontology evaluation will take into account representation of individual ontologies, performance (in terms of accuracy, domain coverage and the efficiency and quality of automated reasoning using the ontologies) on tasks for which the ontology is designed and used, degree of alignment with other ontologies and their compatibility with automated reasoning. A sound and systematic approach to ontology evaluation is required to transform ontology engineering into a true scientific and engineering discipline. This chapter discusses issues and problems in ontology evaluation, describes some current strategies, and suggests some approaches that might be useful in the future.

TIME 2010 Committees

computer.org

General Chair Ian Pratt-Hartmann, University of Manchester, UK ... Program Committee Chairs Nicol... more General Chair Ian Pratt-Hartmann, University of Manchester, UK ... Program Committee Chairs Nicolas Markey, CNRS & ENS Cachan, France Jef Wijsen, University of Mons, Belgium ... Organization Chair Nicolas Markey, CNRS & ENS Cachan, France ... Program Committee Alessandro Artale, Free University of Bozen-Bolzano, Italy Howard Barringer, University of Manchester, UK Béatrice Bérard, University Paris 6-Pierre & Marie Curie, France Claudio Bettini, University of Milan, Italy Davide Bresolin, University of Verona, Italy Thomas Brihaye, University of ...

The Computational Treatment of Nominals

Additional copies of these proceedings may be ordered while stocks last from: Association for Com... more Additional copies of these proceedings may be ordered while stocks last from: Association for Computational Lingustics (ACL) 75 Paterson Street, Suite 9 New Brunswick, NJ 08901 USA Tel: +1-732-342-9100 Fax: +1-732-873-0014 rasmusse© cs. rutger s. edu ... ORGANIZING COMMITTEE: Federica Busa (Brandeis University) Inderjeet Mani (The MITRE Corporation) Patrick Saint-Dizier (IRIT, Universit~ Paul Sabatier) ... PROGRAM COMMITTEE: Federica Busa (Brandeis University) Mark Gawron (SRI International) Bob Ingria (Psyche Systems Corporation) ...

Narrative summarization: Résumé automatique de textes

TAL. Traitement automatique des langues, 2004

Résumé/Abstract La compréhension et le résumé automatique de la narration sont difficiles, en rai... more Résumé/Abstract La compréhension et le résumé automatique de la narration sont difficiles, en raison de l'incapacité des systèmes automatiques d'identfier le vrai contenu de l'information. Ceci peut avoir comme conséquence le choix inadéquat du contenu aussi bien que l'incohérence du résumé. Cet article présente une nouvelle conception pour le résumé automatique de la narration, qui repose sur l'exploitation d'information temporelle. Cette conception distingue trois niveaux: scène, histoire et intrigue. L'article décrit comment ...

Introduction to the special issue on temporal information processing

ACM Transactions on Asian Language Information Processing, 2004

Time is a key dimension of our information space, with many applications standing to benefit from... more Time is a key dimension of our information space, with many applications standing to benefit from exploiting it. This special issue is devoted to temporal information processing for natural language as well as temporal reasoning. We begin by describing some of the ways time is expressed in natural language, and the particular requirements this imposes on information processing systems. We then provide an overview of current annotation-based approaches to temporal information extraction, followed by an introduction to the relevant literature on temporal reasoning. We also provide brief synopses of the articles in this issue, situating them in a broader context. We end with administrative remarks about the creation of this special issue.

Predicting Reader Response in Narrative

This paper sketches a theory of how readers (or users, or players, or viewers) respond to narrati... more This paper sketches a theory of how readers (or users, or players, or viewers) respond to narratives. Such a theory can be useful for developing evaluation functions to allow for narrative outcomes that have maximum impact at particular times on the reader. The reader's response is viewed in terms of character evaluations, namely judgments of sympathy or antipathy for the agent involved in that outcome. Character development is computed in terms of transitions in reader evaluations for an agent over the time course of the narrative. To formally model character evaluations, we begin with a representation of the narrative fabula in terms of the events, their participant roles, and their temporal relations. This representation is implemented on a corpus of narratives with existing tools and standards. Reader evaluations are annotated on events in the fabula. Once high reliability in human character evaluations has been proven, a character evaluation tagger will be trained on these evaluations.

Annotation of Temporal Relations with Tango

Temporal annotation is a complex task characterized by low markup speed and low inter-annotator a... more Temporal annotation is a complex task characterized by low markup speed and low inter-annotator agreements scores. Tango is a graphical annotation tool for temporal relations. It is developed for the TimeML annotation language and allows annotators to build a graph that resembles a timeline. Temporal relations are added by selecting events and drawing labeled arrows between them. Tango is integrated

Guidelines for annotating temporal information

Human Language Technology, 2000

This paper introduces a set of guidelines for annotating time expressions with a canonicalized re... more This paper introduces a set of guidelines for annotating time expressions with a canonicalized representation of the times they refer to. Applications that can benefit from such an annotated corpus include information extraction (e.g., normalizing temporal references for database entry), question answering (answering "when" questions), summarization (temporally ordering information), machine translation (translating and normalizing temporal references), and information visualization (viewing

Summarization Evaluation: An Overview

North American Chapter of the Association for Computational Linguistics, 2001

This paper provides an overview of different meth- ods for evaluating automatic summarization sys... more This paper provides an overview of different meth- ods for evaluating automatic summarization systems. The challenges in evaluating summaries are charac- terized. Both intrinsic and extrinsic approaches are discussed. Methods for assessing informativeness and coherence are described. The advantages and disad- vantages of specific methods are assessed, along with criteria for choosing among them. The paper con- cludes with some

Towards content-based browsing of broadcast news video

Multimedia Information Retrieval, 1997

... Published in: · Book. Intelligent multimedia information retrieval. MIT Press Cambridge, MA, ... more

Producing Biographical Summaries: Combining Linguistic Knowledge with Corpus Statistics

Meeting of the Association for Computational Linguistics, 2001

We describe a biographical multi-document summarizer that summarizes information about people des... more We describe a biographical multi-document summarizer that summarizes information about people described in the news. The summarizer uses corpus statistics along with linguistic knowledge to select and merge descriptions of people from a document collection, removing redundant descriptions. The summarization components have been extensively evaluated for coherence, accuracy, and non-redundancy of the descriptions produced.

The TIPSTER SUMMAC Text Summarization Evaluation

The,TIPSTER Text,Summarization Evaluation (SUMMAC) has established definitively that automatic,te... more The,TIPSTER Text,Summarization Evaluation (SUMMAC) has established definitively that automatic,text summarization is very effective in relevance assessment,tasks. Summaries,as short as 17% of full text length sped up decisionmaking,by almost,a factor of 2 with no statistically significant degradation,in Fscore accuracy. SUMMAC has also introduced,a new intrinsic method,for automated,evaluation of informative,summaries.

Improving Summaries by Revising Them

Meeting of the Association for Computational Linguistics, 1999

This paper describes a program which revises a draft text by aggregating together descriptions of... more This paper describes a program which revises a draft text by aggregating together descriptions of discourse entities, in addition to deleting ex- traneous information. In contrast to knowledge- rich sentence aggregation approaches explored in the past, this approach exploits statistical parsing and robust coreference detection. In an evaluation involving revision of topic-related summaries using informativeness measures from the TIPSTER SUMMAC

A Multilingual Approach to Annotating and Extracting Temporal Information1

Meeting of the Association for Computational Linguistics, 2000

This paper introduces a set of guidelines for annotating time expressions with a canonicalized re... more

The tipster summac text summarization evaluation final report

The TIPSTER Text Summarization Evaluation (SUMMAC) has established definitively that automatic te... more The TIPSTER Text Summarization Evaluation (SUMMAC) has established definitively that automatic text summarization is very effective in relevance assessment tasks. Summaries as short as 17% of full text length sped up decisionmaking by almost a factor of 2 with no statistically significant degradation in Fscore accuracy. SUMMAC has also introduced a new intrinsic method for automated evaluation of informative summaries.

Summarizing Similarities and Differences Among Related Documents

Information Retrieval, 1999

In many modern information retrieval applications, a common problem which arises is the existence... more In many modern information retrieval applications, a common problem which arises is the existence of multiple documents covering similar information, as in the case of multiple news stories about an event or a sequence of events. A particular challenge for text summarization is to be able to summarize the similarities and differences in information content among these documents. The approach described here exploits the results of recent progress in information extraction to represent salient units of text and their relationships. By exploiting meaningful relations between units based on an analysis of text cohesion and the context in which the comparison is desired, the summarizer can pinpoint similarities and differences, and align text segments. In evaluation experiments, these techniques for exploiting cohesion relations result in summaries which (i) help users more quickly complete a retrieval task (ii) result in improved alignment accuracy over baselines, and (iii) improve identification of topic-relevant similarities and differences.

Multi-Document Summarization by Graph Search and Matching

Computing Research Repository, 1997

We describe a new method for summarizing similar- ities and dierences in a pair of related docume... more We describe a new method for summarizing similar- ities and dierences in a pair of related documents using a graph representation for text. Concepts de- noted by words, phrases, and proper names in the document are represented positionally as nodes in the graph along with edges corresponding to semantic re- lations between items. Given a perspective in terms of which

Inferring temporal ordering of events in news

Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology companion volume of the Proceedings of HLT-NAACL 2003--short papers - NAACL '03, 2003

This paper describes a domain-independent, machine-learning based approach to temporally anchorin... more

A pilot study on acquiring metric temporal constraints for events

Proceedings of the Workshop on Annotating and Reasoning about Time and Events - ARTE '06, 2006

Previous research on temporal anchoring and ordering has focused on the annotation and learning o... more Previous research on temporal anchoring and ordering has focused on the annotation and learning of temporal relations between events. These qualitative relations can be usefully supplemented with information about metric constraints, specifically as to how long events last. This paper describes the first steps in acquiring metric temporal constraints for events. The work is carried out in the context of the TimeML framework for marking up events and their temporal relations. This pilot study examines the feasibility of acquisition of metric temporal constraints from corpora.

Recent developments in temporal information extraction

Current Issues in Linguistic Theory, 2004

The growing interest in practical NLP applications such as text summarization and question-answer... more The growing interest in practical NLP applications such as text summarization and question-answering places increasing demands on the processing of temporal information in natural languages. To support this, several new capabilities have emerged. These include the ability to tag events and time expressions, to temporally anchor and order events, and to build models of the temporal structure of discourse. This paper describes some of the techniques and the further challenges that arise.