Recurrent neural network learning for text routing

Stefan Wermter, Christo Panchev, Garen Arevian

Research output: Chapter in Book/Report/Conference proceedingConference proceedingpeer-review

17 Citations (Scopus)


Describes recurrent plausibility networks with internal recurrent hysteresis connections. These recurrent connections in multiple layers encode the sequential context of word sequences. We show how these networks can support text routing of noisy newswire titles according to different given categories. We demonstrate the potential of these networks using an 82 339 word corpus from the Reuters newswire, reaching recall and precision rates above 92%. In addition, we carefully analyze the internal representation using cluster analysis and output representations using a new surface error technique. In general, based on the current recall and precision performance, as well as the detailed analysis, we show that recurrent plausibility networks hold a lot of potential for developing learning and robust newswire agents for the internet.
Original languageEnglish
Title of host publicationProceedings of the International Conference on Artificial Neural Networks
EditorsA Hyvarinen
Number of pages6
ISBN (Print)0 85296 721 7
Publication statusPublished - 1999
Externally publishedYes
Event9th International Conference on Artificial Neural Networks - Edinburgh, United Kingdom
Duration: 7 Sept 199910 Sept 1999
Conference number: 9


Conference9th International Conference on Artificial Neural Networks
Abbreviated titleICANN '99
Country/TerritoryUnited Kingdom


Dive into the research topics of 'Recurrent neural network learning for text routing'. Together they form a unique fingerprint.

Cite this