Supervised language modeling for temporal resolution of texts

We investigate temporal resolution of documents, such as determining the date of publication of a story based on its text. We describe and evaluate a model that build histograms encoding the probability of different temporal periods for a document. We construct histograms based on the Kullback-Leibler Divergence between the language model for a test document and supervised language models for each interval. Initial results indicate this language modeling approach is effective for predicting the dates of publication of short stories, which contain few explicit mentions of years. Categories and Subject Descriptors H.3.1 [Content Analysis and Indexing] General Terms Algorithms, Design, Experimentation, Performance Keywords time, temporal information, text mining, document dating

• Type: Journal
• Year: 2011
• Where: CIKM
• Authors: Abhimanu Kumar, Matthew Lease, Jason Baldridge
• Keywords: CIKM 2011, Dates Of Publication, Information Technology, Language Model, Language Models