Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Search Publications by: Hoa T. Dang (Fed)

Displaying 26 - 36 of 36

Mind the Gap: Dangers of Divorcing Evaluations of Summary Content from Linguistic Quality

August 18, 2008

Author(s)

Hoa T. Dang, John M. Conroy

In this paper, we analyze the state of current human and automatic evaluation of topic-focused summarization in the Document Understanding Conference main task for 2005-2007. The analyses show that while ROUGE has very strong correlation with

DUC in Context

November 21, 2007

Author(s)

Paul D. Over, Hoa T. Dang, Donna K. Harman

Recent years have seen increased interest in text summarization with emphasis on evaluation of prototype ststems. Many factors can affect the design of such evaluations, requiring choices among competing alternatives. This paper examines several major

Different Structures for Evaluating Answers to Complex Questions: Pyramids Are Stable, and So Are Human Assessors

June 23, 2007

Author(s)

Hoa T. Dang, Jimmy Lin

The idea of ``nugget pyramids'' has recently been introduced as a refinement to the nugget-based methodology employed to evaluate answers to complex questions in the Text Retrieval Conference (TREC) Question Answering (QA) tracks. This work examines data

DUC 2005: Evaluation of Question-Focused Summarization Systems

January 22, 2007

Author(s)

Hoa T. Dang

The Document Understanding Conference (DUC) 2005 evaluation had a single user-oriented, question-focused summarization task, which was to synthesize from a set of 25-50 documents a well-organized, fluent answer to a complex question. The evaluation shows

Overview of the TREC 2005 Question Answering Track

October 2, 2006

Author(s)

Ellen M. Voorhees, Hoa T. Dang

The TREC 2005 Question Answering (QA) track contained three tasks: the main question answering task, the document ranking task, and the relationship task. In the main task, question series were used to define a set of targets. Each series was about a

The Role of Semantic Roles in Disambiguating Verb Senses

December 19, 2005

Author(s)

Hoa T. Dang, Martha S. Palmer

We describe an automatic Word Sense Disambiguation (WSD) system that disambiguates verb senses using syntactic and semantic features that encode information about predicate arguments and semantic classes. Our system performs better than the best published