A Proposed Language Model Based on LSTM

Zhang, Yumeng and Lu, Xuanmin and Quan, Bei and Wei, Yuanyuan (2019) A Proposed Language Model Based on LSTM. In: IoT as a Service. 4th EAI International Conference, IoTaaS 2018, Xi’an, China, November 17–18, 2018, Proceedings.

[thumbnail of 29602.pdf] PDF
29602.pdf

Download (873kB)

Abstract

In view of the shortcomings of language model N-gram, this paper presents a Long Short-Term Memory (LSTM)-based language model based on the advantage that LSTM can theoretically utilize any long sequence of information. It’s an improved RNN model. Experimental results show that the perplexity of the LSTM language model in the PBT corpus is only one-half that of the N-gram language model.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Date Deposited: 04 Mar 2026 11:43
Last Modified: 20 Nov 2026 13:42
URI: https://eprints.eai.eu/id/eprint/20531

Actions (login required)

View Item
View Item