Description of the Google update summarizer at TAC-2011
نویسندگان
چکیده
In this paper we describe the system with which we have participated at TAC-2011 in the task of update summarization. This is our first participation in TAC, and we have started exploring the use of topic models for summarization. We have participated with a lightweight system that is an extension of TOPICSUM (Haghighi and Vanderwende, 2009), which we are currently extending for update summarization. The system had almost no pre-processing nor post-processing. The resulting scores rank as average across all participants. In this paper we analyze the results and outline some ideas for improvement.
منابع مشابه
Sentence Position revisited: A robust light-weight Update Summarization baseline Algorithm
In this paper, we describe a sentence position based summarizer that is built based on a sentence position policy, created from the evaluation testbed of recent summarization tasks at Document Understanding Conferences (DUC). We show that the summarizer thus built is able to outperform most systems participating in task focused summarization evaluations at Text Analysis Conferences (TAC) 2008. ...
متن کاملJRC's Participation at TAC 2011: Guided and MultiLingual Summarization Tasks
The paper describes our participation in the Guided and Multilingual Summarization Tasks at the Text Analysis Conference 2011 (TAC’11). We participated in the Guided task with the system from the previous year which combines aspect identification by an event extraction system and automatically learned lexicons with LSA-based summarizer. This year we included temporal analysis to improve sentenc...
متن کاملSUTLER: Update Summarizer Based on Latent Topics
This paper deals with our past and recent research in text summarization. We went from single-document summarization through multidocument summarization to update summarization. We describe the development of our summarizer which is based on latent semantic analysis (LSA). The classical LSA-based summarization model was improved by Iterative Residual Rescaling. We propose the update summarizati...
متن کاملThe LIA Update Summarization Systems at TAC 2008 (DRAFT)
For the third participation of the LIA to the DUC–TAC conferences, two summarizers were developed. The first is based on the SMMR sentence scoring algorithm described in (Boudin et al., 2008). The second summarizer is a fusion between two sentence scoring methods: SMMR and a variable length insertion gap n-term model (Favre et al., 2006; Boudin et al., 2007). We compare our two summarizers usin...
متن کاملMulti-Document Summarization using Automatic Key-Phrase Extraction
The development of a multi-document summarizer using automatic key-phrase extraction has been described. This summarizer has two main parts; first part is automatic extraction of Key-phrases from the documents and second part is automatic generation of a multidocument summary based on the extracted key-phrases. The CRF based Automatic Keyphrase extraction system has been used here. A document g...
متن کامل