Warren Greiff - Academia.edu (original) (raw)
Papers by Warren Greiff
this paper is structured as follows: first we describe the development tools just mentioned. Then... more this paper is structured as follows: first we describe the development tools just mentioned. Then we discuss our work on candidate ranking and provide a number of relevant results. Finally we talk about our end-to-end experiments and make some concluding remarks
Bookmarks Related papers MentionsView impact
Proceedings of HLT- …, 2004
Bookmarks Related papers MentionsView impact
Natural Language Engineering, 2006
Reading comprehension (RC) tests involve reading a short passage of text and answering a series o... more Reading comprehension (RC) tests involve reading a short passage of text and answering a series of questions pertaining to that text. We present a methodology for evaluation of the application of modern natural language technologies to the task of responding to RC tests. Our work is based on ABCs (Abduction Based Comprehension system), an automated system for taking tests requiring short answer phrases as responses. A central goal of ABCs is to serve as a testbed for understanding the role that various linguistic components play in responding to reading comprehension questions. The heart of ABCs is an abductive inference engine that provides three key capabilities: (1) first-order logical representation of relations between entities and events in the text and rules to perform inference over such relations, (2) graceful degradation due to the inclusion of abduction in the reasoning engine, which avoids the brittleness that can be problematic in knowledge representation and reasoning ...
Bookmarks Related papers MentionsView impact
Information Processing & Management, 2003
Bookmarks Related papers MentionsView impact
Voorhees and Harman [21], Nov 13, 2000
1 In keeping with our marine theme, we considered renaming our system Flounder due to its poor pe... more 1 In keeping with our marine theme, we considered renaming our system Flounder due to its poor performance this year. A trivial bug in the answer candidate ranking system caused candidates to be ranked essentially at random. Perhaps this run should be considered a “chance” baseline.
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Proceedings of the First International Conference on Human Language Technology Research, Mar 18, 2001
Bookmarks Related papers MentionsView impact
ABSTRACT We present the design and development of a Hidden Markov Model for the division of news ... more ABSTRACT We present the design and development of a Hidden Markov Model for the division of news broadcasts into story segments. Model topology, and the textual features used, are discussed, together with the non-parametric estimation techniques that were employed ...
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
This paper reports our on-going efforts to exploit multiple features derived from an audio stream... more This paper reports our on-going efforts to exploit multiple features derived from an audio stream using source material such as broadcast news, teleconferences, and meetings. These features are derived from algorithms including automatic speech recognition, automatic speech indexing, speaker identification, prosodic and audio feature extraction. We describe our research prototype - the Audio Hot Spotting System - that allows users
Bookmarks Related papers MentionsView impact
In this paper, we describe MITRE's contribution to the logical form generation track of Sense... more In this paper, we describe MITRE's contribution to the logical form generation track of Senseval-3. We begin with a description of the context of MITRE's work, followed by a description of the MITRE sys- tem and its results. We conclude with a commentary on the form and structure of this evaluation track.
Bookmarks Related papers MentionsView impact
Advances in Video, Audio, and Imagery Analysis for Search, Data Mining, Surveillance, and Authoring, 2012
Bookmarks Related papers MentionsView impact
Proceedings of the Workshop on Interdisciplinary Approaches to Speech Indexing and Retrieval at HLT-NAACL 2004 - SpeechIR '04, 2004
Bookmarks Related papers MentionsView impact
ACM SIGIR Forum, 1997
The inference network model of information retrieval allows for a probabilistic interpretation of... more The inference network model of information retrieval allows for a probabilistic interpretation of Boolean query operators. Prior work has shown, however, that these operators do not perform as well as the pnorrn operators developed in the context of the vector space model. The design of alternativeoperators in the inference network framework must contend with the issue of computational tractability. We define a flexible class of link matrices that are natural candidates for the implementation of Boolean operators and art 0(n2) algorithm for the computation of ...
Bookmarks Related papers MentionsView impact
Proceedings of HLT-NAACL 2004: Short Papers on XX - HLT-NAACL '04, 2004
Bookmarks Related papers MentionsView impact
Proceedings of the eleventh international conference on Information and knowledge management - CIKM '02, 2002
In probabilistic approaches to information retrieval, the occurrence of a query term in a documen... more In probabilistic approaches to information retrieval, the occurrence of a query term in a document contributes to the probability that the document will be judged relevant. It is typically assumed that the weight assigned to a query term should be based on the expected value of that contribution. In this paper we show that the degree to which observable document
Bookmarks Related papers MentionsView impact
Proceedings of the first international conference on Human language technology research - HLT '01, 2001
Bookmarks Related papers MentionsView impact
User Modeling and User-Adapted Interaction, 2000
Bookmarks Related papers MentionsView impact
Information Processing & Management, 2010
Bookmarks Related papers MentionsView impact
this paper is structured as follows: first we describe the development tools just mentioned. Then... more this paper is structured as follows: first we describe the development tools just mentioned. Then we discuss our work on candidate ranking and provide a number of relevant results. Finally we talk about our end-to-end experiments and make some concluding remarks
Bookmarks Related papers MentionsView impact
Proceedings of HLT- …, 2004
Bookmarks Related papers MentionsView impact
Natural Language Engineering, 2006
Reading comprehension (RC) tests involve reading a short passage of text and answering a series o... more Reading comprehension (RC) tests involve reading a short passage of text and answering a series of questions pertaining to that text. We present a methodology for evaluation of the application of modern natural language technologies to the task of responding to RC tests. Our work is based on ABCs (Abduction Based Comprehension system), an automated system for taking tests requiring short answer phrases as responses. A central goal of ABCs is to serve as a testbed for understanding the role that various linguistic components play in responding to reading comprehension questions. The heart of ABCs is an abductive inference engine that provides three key capabilities: (1) first-order logical representation of relations between entities and events in the text and rules to perform inference over such relations, (2) graceful degradation due to the inclusion of abduction in the reasoning engine, which avoids the brittleness that can be problematic in knowledge representation and reasoning ...
Bookmarks Related papers MentionsView impact
Information Processing & Management, 2003
Bookmarks Related papers MentionsView impact
Voorhees and Harman [21], Nov 13, 2000
1 In keeping with our marine theme, we considered renaming our system Flounder due to its poor pe... more 1 In keeping with our marine theme, we considered renaming our system Flounder due to its poor performance this year. A trivial bug in the answer candidate ranking system caused candidates to be ranked essentially at random. Perhaps this run should be considered a “chance” baseline.
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Proceedings of the First International Conference on Human Language Technology Research, Mar 18, 2001
Bookmarks Related papers MentionsView impact
ABSTRACT We present the design and development of a Hidden Markov Model for the division of news ... more ABSTRACT We present the design and development of a Hidden Markov Model for the division of news broadcasts into story segments. Model topology, and the textual features used, are discussed, together with the non-parametric estimation techniques that were employed ...
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
This paper reports our on-going efforts to exploit multiple features derived from an audio stream... more This paper reports our on-going efforts to exploit multiple features derived from an audio stream using source material such as broadcast news, teleconferences, and meetings. These features are derived from algorithms including automatic speech recognition, automatic speech indexing, speaker identification, prosodic and audio feature extraction. We describe our research prototype - the Audio Hot Spotting System - that allows users
Bookmarks Related papers MentionsView impact
In this paper, we describe MITRE's contribution to the logical form generation track of Sense... more In this paper, we describe MITRE's contribution to the logical form generation track of Senseval-3. We begin with a description of the context of MITRE's work, followed by a description of the MITRE sys- tem and its results. We conclude with a commentary on the form and structure of this evaluation track.
Bookmarks Related papers MentionsView impact
Advances in Video, Audio, and Imagery Analysis for Search, Data Mining, Surveillance, and Authoring, 2012
Bookmarks Related papers MentionsView impact
Proceedings of the Workshop on Interdisciplinary Approaches to Speech Indexing and Retrieval at HLT-NAACL 2004 - SpeechIR '04, 2004
Bookmarks Related papers MentionsView impact
ACM SIGIR Forum, 1997
The inference network model of information retrieval allows for a probabilistic interpretation of... more The inference network model of information retrieval allows for a probabilistic interpretation of Boolean query operators. Prior work has shown, however, that these operators do not perform as well as the pnorrn operators developed in the context of the vector space model. The design of alternativeoperators in the inference network framework must contend with the issue of computational tractability. We define a flexible class of link matrices that are natural candidates for the implementation of Boolean operators and art 0(n2) algorithm for the computation of ...
Bookmarks Related papers MentionsView impact
Proceedings of HLT-NAACL 2004: Short Papers on XX - HLT-NAACL '04, 2004
Bookmarks Related papers MentionsView impact
Proceedings of the eleventh international conference on Information and knowledge management - CIKM '02, 2002
In probabilistic approaches to information retrieval, the occurrence of a query term in a documen... more In probabilistic approaches to information retrieval, the occurrence of a query term in a document contributes to the probability that the document will be judged relevant. It is typically assumed that the weight assigned to a query term should be based on the expected value of that contribution. In this paper we show that the degree to which observable document
Bookmarks Related papers MentionsView impact
Proceedings of the first international conference on Human language technology research - HLT '01, 2001
Bookmarks Related papers MentionsView impact
User Modeling and User-Adapted Interaction, 2000
Bookmarks Related papers MentionsView impact
Information Processing & Management, 2010
Bookmarks Related papers MentionsView impact