Unified Parallel Intent and Slot Prediction with Cross Fusion and Slot Masking

Autor:	Bharatram Natarajan, Gaurav Mathur, Jun-seong Kim, Anmol Bhasin, Joo Hyuk Jeon
Rok vydání:	2019
Předmět:	Fusion Computer science Parallel architecture Data mining computer.software_genre computer Masking (Electronic Health Record) Convolutional neural network Utterance
Zdroj:	Natural Language Processing and Information Systems ISBN: 9783030232801 NLDB
Popis:	In Automatic Speech Recognition applications, Natural Language Processing (NLP) has sub-tasks of predicting the Intent and Slots for the utterance spoken by the user. Researchers have done a lot of work in this field using Recurrent-Neural-Networks (RNN), Convolution Neural Network (CNN) and attentions based models. However, all of these use either separate independent models for both intent and slot or sequence-to-sequence type networks. They might not take full advantage of relation between intent and slot learning. We are proposing a unified parallel architecture where a CNN Network is used for Intent Prediction and Bidirectional LSTM is used for Slot Prediction. We used Cross Fusion technique to establish relation between Intent and Slot learnings. We also used masking for slot prediction along with cross fusion. Our models surpass existing state-of-the-art results for both Intent as well as Slot prediction on two open datasets.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::f7dcb4f6f32d7cd1eea5efb8d212d002 https://doi.org/10.1007/978-3-030-23281-8_22 Zobrazit plný text záznamu