Dynamic Coreference-Based Summarization

Breck Baldwin, Thomas S. Morton

Abstract: \Ve ha.ve developed a query-sensitive text summarization technology \Vell suited for the task of determining whether a. document is relevant to <'-" query. Enoug;h of the docurnent is displayed for the user to determine whether the document should l:H~ read in its entirety. Evaluations indicate that sununarics are classif-ied for relevauce uearly as well as full documents. This approach i.s based on the concept that a good SltJnrnary will repn-)sent each of the topics in the query and is n'alized by ~electing smltcnc<-!S from the document until all the phrases in the query which are represented in the sumiHa.ry are (covered.' A phrase in th<:; docu. ' Jllcnt is considered to cover a phraf:le in the qu(~r:Y if it is cmeferent \Vith it. This approach maxirnizes the space of <!ntities reta.incd in th(:: summ<Jxy with minimal rednnda.ncy. 'rhe software is built upon the CAMP NLP spt.cm [2].