TimeMines: Constructing Timelines with Statistical Models of Word Usage

By R. Swan, David D. Jensen. 2000

122 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Discovering Diverse and Salient Threads in Document Collections (2012, background): “Swan and Jensen (2000) proposed a system for ﬁnding temporally clustered named entities in news text and presenting them on a timeline.”
Topics over time: a non-Markov continuous-time model of topical trends (2006, unknown): “In all cases, for simplicity, we ﬁx the number of topics T = 50 .”
Bursty and Hierarchical Structure in Streams (2002, methodology): “The development here will use a cost model q q q q 0 1 2 3 qi transition cost transition cost 0 emissions at rate -1 si g”
Time-based language models (2003, background): “There has been work on constructing timelines automatically from time-tagged retrieved documents as a visualization and discovery tool (e.g. [7, 8]).”
Trains of thought: generating information maps (2012, background): “Previous news summarization systems with structured output [Swan and Jensen, 2000, Yan et al., 2011, Allan et al., 2001] have focused mostly on timeline generation.”