Boris Katz, Matthew Bilotti, Sue Felshin, Aaron Fern, Wesley Hildebr, Roni Katzir, ...
multiple questions on a topic from heterogeneous resources
Duplicate Removal for Candidate Answer Sentences (2008)
Yuan Shen, Gabriel Zaccak, Boris Katz, Yuan Luo, Ozlem Uzuner
In this paper, we describe the duplicate removal component of Infolab’s 1 question answering system that contributed to CSAIL’s entry of TREC-15 2 Question Answering track. The goal of the...
Stylistics for Text Retrieval in Practice (2008)
Ozlem Uzuner, Shlomo Argamon, Jussi Karlgren
Stylistics for Text Retrieval in Practice has met during SIGIR 2006. With participants from both academia and industry, the workshop spurred interesting discussions on the future of stylistics, its...
Boris Katz, Matthew Bilotti, Sue Felshin, Aaron Fern, Wesley Hildebr, Roni Katzir, ...
multiple questions on a topic from heterogeneous resources
Recognizing Text Similarity (2008)
Ozlem Uzuner, All Davis, Boris Katz
Overview: There are a variety of circumstances under which it would be useful to determine that two documents contain similar text, including detecting plagiarism and copyright infringement, and...
Non-Verbatim Copyright Infringement Detection for Text (2008)
The Problem: Copyright infringement is a serious problem which threatened authors of creative works even in the non-electronic world. In the electronic world, easy access to electronic documents and...
Virtual Markets in Wireless Grids: Peering Policy Prospects (2008)
Professor Lee, W. Mcknight, Ozlem Uzuner, Phd Candidate, Diana Anius
Paper prepared for presentation at:
Word Sense Disambiguation For Information Retrieval (2008)
Boris Katz, Ozlem Uzuner, Deniz Yuret
The Problem: Despite the increasing importance of Information Retrieval (IR) systems as data retrieval tools, the performance of most of these systems has not yet reached a satisfactory level. Word...
Sales Taxes on the Internet: When and How to Tax? (2007)
As a first attempt to tax electronic commerce, many countries applied the existing tax laws to Internet. However, applying these laws to border-spanning electronic commerce proved very inefficient...
Better Public Policy through Natural Language Information Access (2007)
Boris Katz, Roger Hurwitz, Jimmy J. Lin, Ozlem Uzuner
Federal agencies implement laws passed by the Congress by creating rules and regulations that can be applied in practice. During this process, staffs at the various agencies may review past and...
Stylistics for text retrieval in practice (2006)
Uzuner, Ozlem, Argamon, Shlomo, Karlgren, Jussi
Stylistics for Text Retrieval in Practice has met during SIGIR 2006. With participants from both academia and industry, the workshop spurred interesting discussions on the future of stylistics, its...
Relationships in Patient Records (2006)
Tawanda Carleton Sibanda, Ozlem Uzuner, Tawanda Carleton Sibanda
Role of Local Context in Automatic Deidentification of Ungrammatical, Fragmented Text (2006)
Deidentification of clinical records is a crucial step before these records can be distributed to non-hospital researchers. Most approaches to deidentification rely heavily on dictionaries and...
Contents TrendMine: Utilizing Authorship Profiling and Tone Analysis in Context 4 (2006)
Ozlem Uzuner, Michael Gamon, Julio Gonzalo, Iryna Gurevych, Gary Kacmarcik, Gilad Mishne, ...
Role of Local Context in Automatic Deidentification of Ungrammatical, Fragmented Text (2006)
Deidentification of clinical records is a crucial step before these records can be distributed to non-hospital researchers. Most approaches to deidentification rely heavily on dictionaries and...
Identifying Expression Fingerprints using Linguistic Information (2005)
This thesis presents a technology to complement taxation-based policy proposals aimed at addressing the digital copyright problem. Theapproach presented facilitates identification of intellectual...
Identifying Expression Fingerprints using Linguistic Information (2005)
This thesis presents a technology to complement taxation-based policy proposals aimed at addressing the digital copyright problem. Theapproach presented facilitates identification of intellectual...
Lexical Chains and Sliding Locality Windows in Content-based Text Similarity Detection (2005)
Nahnsen, Thade, Uzuner, Ozlem, Katz, Boris
We present a system to determine content similarity of documents. More specifically, our goal is to identify book chapters that are translations of the same original chapter; this task requires...
Lexical Chains and Sliding Locality Windows in Content-based Text Similarity Detection (2005)
Nahnsen, Thade, Uzuner, Ozlem, Katz, Boris
We present a system to determine content similarity of documents. More specifically, our goal is to identify book chapters that are translations of the same original chapter; this task requires...
Distribution Volume Tracking on Privacy-Enhanced Wireless Grid (2004)
In this paper, we discuss a wireless grid in which users are highly mobile, and form ad-hoc and sometimes short-lived connections with other devices. As they roam through networks, the users may...
Distribution Volume Tracking on Privacy-Enhanced Wireless Grid (2004)
In this paper, we discuss a wireless grid in which users are highly mobile, and form ad-hoc and sometimes short-lived connections with other devices. As they roam through networks, the users may...
Using empirical methods for evaluating expression and content similarity (2004)
Ozlem Uzuner, All Davis, Boris Katz
Despite lack of any significant quantifiable similarities between documents, people can intuitively compare documents and evaluate their similarity. To understand how people evaluate text similarity,...
Using Empirical Methods for Evaluating Expression and Content Similarity (2004)
Ozlem Uzuner, Randall Davis, All Davis, Boris Katz
Despite lack of any significant quantifiable similarities between documents, people can intuitively compare documents and evaluate their similarity. To understand how people evaluate text similarity,...
Answering Multiple Questions on a Topic from Heterogeneous Resources (2004)
Boris Katz, Matthew Bilotti, Sue Felshin, Aaron Fernandes, Wesley Hildebrandt, Roni Katzir, ...
this paper we will call "topics" to dif- ferentiate them from the "focus" (which has been called the "target" of a factoid or list question) of each individual question...
Dr. Junseok Hwang, Dr. Hwa Chang, James Howison, Praveen Aravamudham, Ozlem Uzuner
Tufts University
Better Public Policy through Natural Language Information Access (2003)
Boris Katz, Roger Hurwitz, Jimmy J. Lin, Ozlem Uzuner
be applied in practice. During this process, staffs at the various agencies may review past and current regulations and receive comments from stakeholders and the public regarding the proposed...
Ozlem Uzuner, Randall Davis, All Davis
Recent technological developments have created new challenges for the protection and enforcement of intellectual property rights. The amendments to existing legislation in response to these...
Sales Tax on the Internet: When and How to Tax? (2002)
As a first attempt to tax electronic commerce, many countries applied the existing tax laws to Internet. However, applying these laws to border-spanning electronic commerce proved very inefficient...
Sales Tax on the Internet: When and How to Tax? (2002)
As a first attempt to tax electronic commerce, many countries applied the existing tax laws to Internet. However, applying these laws to border-spanning electronic commerce proved very inefficient...
Peering Policy Obstacles (2002)
Lee W. Mcknight, Diana Anius, Ozlem Uzuner, Professor Lee, W. Mcknight, Ozlem Uzuner, ...
please visit our website at
Word-sense Disambiguation Applied to Information Retrieval. M.Eng thesis (1998)
distribute publicly paper and electronic copies of this thesis and to grant others the right to do so. Auor Certified by.
Syntactically-Informed Semantic Category Recognizer for Discharge Summaries
Sibanda, Tawanda, He, Tian, Szolovits, Peter, Uzuner, Ozlem
Semantic category recognition (SCR) contributes to document understanding. Most approaches to SCR fail to make use of syntax. We hypothesize that syntax, if represented appropriately, can improve...