• Publications
  • Influence
ROUGE: A Package for Automatic Evaluation of Summaries
ROUGE stands for Recall-Oriented Understudy for Gisting Evaluation. It includes measures to automatically determine the quality of a summary by comparing it to other (ideal) summaries created byExpand
Automatic Evaluation of Summaries Using N-gram Co-occurrence Statistics
We show that automatic evaluation using unigram co-occurrences between summary pairs correlates surprising well with human evaluations based on various statistical metrics; while direct application of the BLEU evaluation procedure does not always give good results. Expand
Automatic Evaluation of Machine Translation Quality Using Longest Common Subsequence and Skip-Bigram Statistics
We present two new objective automatic evaluation methods for machine translation. Expand
ORANGE: a Method for Evaluating Automatic Evaluation Metrics for Machine Translation
We introduce a new evaluation method, Orange, for evaluating automatic machine translation evaluation metrics automatically without extra human involvement other than using a set of reference translations. Expand
Low-Quality Product Review Detection in Opinion Summarization
This paper addresses the problem of detecting lowquality product reviews. Expand
Finding question-answer pairs from online forums
Online forums contain a huge amount of valuable user generated content. Expand
The Automated Acquisition of Topic Signatures for Text Summarization
We present a method for automatically training topic signatures-sets of related words, with associated weights, organized around head topics and illustrate with signatures we created with 6,194 TREC collection texts. Expand
COM: a generative model for group recommendation
We propose a probabilistic model named COM (COnsensus Model) to model the generative process of group activities, and make group recommendations. Expand
Automated Text Summarization in SUMMARIST
SUMMARIST is an attempt to create a robust automated text summarization system, based on the ‘equation’: summarization = topic identification + interpretation + generation. Expand
Overview of Opinion Analysis Pilot Task at NTCIR-6
This paper describes an overview of the OpinionAnalysis Pilot Task from 2006 to 2007 at the Sixth NT-CIR Workshop. Expand