Some interesting directions in Automatic SummarizationToday’s lectureRelevant Papers :More about DUC 2002 data…DUC 2002 input categoriesTf-idf summary - d061Tf-idf summary - d064Tf-idf summary - d065Multi-strategy summarizationProduce multiple summaries and choose – LCC GISTexterRoute to a specific module – Columbia’s multi-document summarizerFeatures - Single EventFeatures - BiographiesFeatures – Weakly related documentsCharacterizing/ Classifying inputsInput difficulty and Performance Confidence EstimationInput to summarizerInput difficulty & Content coverage scoresDid system performance vary with DUC 2001 input categories?Input type influenced scores obtainedCohesive inputs are easier to summarizeInputs can be easy or difficult =>First step..Features – Simple length-basedFeatures – Word distributions in inputFeatures – Document similarity and relatednessFeatures – Document similarity and relatednessFeatures – Log likelihood ratio basedWhat makes some inputs easy?Input difficulty hypothesis for systemsClassification ResultsSummary Evaluation without Human ModelsNeed for cheap, fast measuresCompare with input – No human modelsWhat features should we use?Features - Divergence between input and summaryFeatures – Use of topic words from the inputFeatures – Similarity between input and summaryFeatures - Summary ProbabilityAnalysis of featuresResultsEvaluation without human modelsOther summarization tasks of interestSlide 44What you have learnt today..1Some interesting directions in Automatic SummarizationAnnie LouisCIS 43012/02/082Today’s lectureMulti-strategy summarizationIs one method enough?Performance Confidence EstimationWould be nice to have an indication of expected system performance on an inputEvaluation without human modelsCan we come up with cheap and fast evaluation measures?Beyond generic summarizationQuery focused, updates, blogs, meeting, speech..3Relevant Papers :Lacatusu et al. LCC’s GISTexter at DUC 2006: Multi-Strategy Multi-Document Summarization. In Proceedings of the Document Understanding Workshop (DUC-2006) McKeown et al. Columbia multi-document. summarization: Approach and evaluation. In Proceedings of the Document Understanding Conference (DUC01), 2001. Nenkova et al. Can You Summarize This? Identifying Correlates of Input Difficulty for Multi-Document Summarization. In Proceedings of ACL-08: HLT4More about DUC 2002 data…/project/cis/nlp/tools/Summarization_Data/Inputs2002 Newswire texts Has 3 categories of inputs ! ?5DUC 2002 input categoriesSingle event - 30 inputsEg: d061- Hurricane GilbertSame place, roughly same time, same actionsMultiple distinct events – 15 inputsEg: d064 - Opening of Mac Donald’s at Russia, Canada, South Korea..Different places, different times, different agentsBiographies – 15 inputsEg: d065 – Dan Quayle, Bush’s nominee for vice presidentOne person – one event, background info – events from the pastDo you think a single method will do well for all ?6Tf-idf summary - d061Hurricane Gilbert Heads Toward Dominican Coast . Tropical Storm Gilbert formed in the eastern Caribbean and strengthened into a hurricane Saturday night. Gilbert Reaches Jamaican Capital With 110 Mph Winds . Hurricane warnings were posted for the Cayman Islands, Cuba and Haiti. Hurricane Hits Jamaica With 115 mph Winds; Communications. Gilbert reached Jamaica after skirting southern Puerto Rico, Haiti and the Dominican Republic. Gilbert was moving west-northwest at 15 mph and winds had decreased to 125 mph. What Makes Gilbert So Strong? With PM-Hurricane Gilbert, Bjt . Hurricane Gilbert Heading for Jamaica With 100 MPH Winds . Tropical Storm Gilbert7Tf-idf summary - d064First McDonald's to Open in Communist Country . Police Keep Crowds From Crashing First McDonald's . McDonald's and Genex contribute $1 million each for the flagship restaurant. A Bolshoi Mac Attack in Moscow as First McDonald's Opens . McDonald's Opens First Restaurant in China . McDonald's hopes to open a restaurant in Beijing later. The 500-seat McDonald's restaurant in a three-story building is operated by McDonald's Restaurant Shenzhen Ltd., a wholly owned subsidiary of McDonald's Hong Kong. McDonald's Hong Kong is a 50-50 joint venture with McDonald's in the United States. McDonald's officials say it is not a question that8Tf-idf summary - d065Tucker was fascinated by the idea, Quayle said. But Dan Quayle's got experience, too. Quayle's Triumph Quickly Tarnished . Quayle's Biography Inflates State Job; Quayle Concedes Error . Her statement was released by the Quayle campaign. But he would go no further in describing what assignments he would give Quayle. ``I will be a very close adviser to the president,'' Quayle said. ``You're never going to see Dan Quayle telling tales out of It was everything Quayle had hoped for. Quayle had said very little and he had said it very well. There are windows into the workings of the9Multi-strategy summarizationMultiple summarization modules within a single systemBetter than a single method How to employ a multi-strategy system?Use all methods, produce multiple summaries, choose bestUse a router and summarize by only one specific method10Produce multiple summaries and choose – LCC GISTexterTask - Query focused summarizationQuery is decomposed by 3 methodsSent to a QA system and a multi-document summarizer6 different summariesSelect the best summaryTextual entailment + pyramid scoring11Route to a specific module – Columbia’s multi-document summarizerFeatures to classify an input asSingle eventBiographyLoosely connected documentsThe result of classification is used to route the input to one of 3 different summarizers12Features - Single EventTo identifyTime span between publication dates < 80 daysMore than 50% documents published on same dayTo summarizeExploit redundancy, cluster similar sentences into themesRank themes based on size, similarity, ranking of contained sentences by lexical chainsSelect phrases from each themeGenerate sentences13Features - BiographiesTo identifyFrequency of most frequent capitalized letter > X (compensate for NE)Frequency of personal pronouns > YTo summarizeTarget individual mentioned in sentence ?Another individual found in the sentence ?Position of most prominent capitalized word in the sentence14Features – Weakly
View Full Document