CPL - Chalmers Publication Library
| Utbildning | Forskning | Styrkeområden | Om Chalmers | In English In English Ej inloggad.

Summarizing online user reviews using bicliques

Azam Sheikh Muhammad ; Peter Damaschke (Institutionen för data- och informationsteknik, Datavetenskap, Algoritmer (Chalmers)) ; Olof Mogren (Institutionen för data- och informationsteknik, Datavetenskap, Algoritmer (Chalmers))
42nd International Conference on Current Trends in Theory and Practice of Computer Science SOFSEM 2016, Lecture Notes in Computer Science Vol. 9587 (2016), p. 569-579.
[Konferensbidrag, refereegranskat]

With vast amounts of text being available in electronic format, such as news and social media, automatic multi-document summarization can help extract the most important information. We present and evaluate a novel method for automatic extractive multi-document summarization. The method is purely combinatorial, based on bicliques in the bipartite word-sentence occurrence graph. It is particularly suited for collections of very short, independently written texts (often single sentences) with many repeated phrases, such as customer reviews of products. The method can run in subquadratic time in the number of documents, which is relevant for the application to large collections of documents.

Nyckelord: extractive summarization, bipartite clique, word frequency

Den här publikationen ingår i följande styrkeområden:

Läs mer om Chalmers styrkeområden  

Denna post skapades 2016-01-20. Senast ändrad 2016-05-12.
CPL Pubid: 230974