• Publications
  • Influence
Summarizing text documents: sentence selection and evaluation metrics
An analysis of news-article summaries generated by sentence selection, using a normalized version of precision-recall curves with a baseline of random sentence selection to evaluate features and empirical results show the importance of corpus-dependent baseline summarization standards, compression ratios and carefully crafted long queries.
Multi-Document Summarization By Sentence Extraction
This paper discusses a text extraction approach to multi-document summarization that builds on single-document summarization methods by using additional, available information about the document set
Bridging the lexical chasm: statistical approaches to answer-finding
It is shown that the task of “answer-finding” differs from both document retrieval and tradition question-answering, presenting challenges different from those found in these problems.
Headline Generation Based on Statistical Translation
This paper presents results on experiments using this approach, in which statistical models of the term selection and term ordering are jointly applied to produce summaries in a style learned from a training corpus.
OCELOT: a system for summarizing Web pages
This paper builds upon recent work in non-extractive summarization, producing the gist of a web page by “translating” it into a more concise representation rather than attempting to extract a text span verbatim.
Comparative Experiments on Sentiment Classification for Online Product Reviews
A series of experiments with different machine learning algorithms are discussed in order to experimentally evaluate various trade-offs, using approximately 100K product reviews from the web.
Statistical Machine Translation for Query Expansion in Answer Retrieval
We present an approach to query expansion in answer retrieval that uses Statistical Machine Translation (SMT) techniques to bridge the lexical gap between questions and answers. SMT-based query
Ultra-summarization (poster abstract): a statistical approach to generating highly condensed non-extractive summaries
This paper presents an alternative statistical model of a summarization process, which jointly applies statistical models of the term selection and term ordering process to produce brief coherent summaries in a style learned from a training corpus.
Ultra-Summarization: A Statistical Approach to Generating Highly Condensed Non-Extractive Summaries (poster abstract).
A game machine which can be played by two or more players includes an elongated box-like housing in which a game ball can be inserted and portions which can move within these spaces so as to cause suitable manipulations of the game ball, including dribbling, when contacted by the noted projector element and activator element portions.
Query-Relevant Summarization using FAQs
Taking a learning approach enables a principled, quantitative evaluation of the proposed system, and the results of some initial experiments suggest the plausibility of learning for summarization.