Abstract
Inspired by bidirectional long short-term memory (LSTM) recurrent neural network (RNN) architectures, commonly applied in natural language processing (NLP) tasks, we have investigated an alternative bidirectional RNN structure consisting of two Echo state networks (ESN). Like the widely applied BiLSTM architectures, the BiESN structure accumulates information from both the left and right contexts of target word, thus accounting for all available information within the text. The main advantages of BiESN over BiLSTM are the smaller number of trainable parameters and a simpler training algorithm. The two modelling approaches have been compared on the word sense disambiguation task (WSD) in NLP. The accuracy of several BiESN architectures is compared with that of similar BiLSTM models trained and evaluated on the same data sets.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
