Parallel Intent And Slot Prediction Using MLB Fusion

Abstract

Intent and Slot Identification are two important tasks in Spoken Language Understanding (SLU). For a natural language utterance, there is a high correlation between these two tasks. A lot of work has been done on each of these using Recurrent-Neural-Networks (RNN), Convolution Neural Networks (CNN) and Attention based models. Most of the past work used two separate models for intent and slot prediction. Some of them also used sequence-to-sequence type models where slots are predicted after evaluating the utterance-level intent. In this work, we propose a parallel Intent and Slot Prediction technique where separate Bidirectional Gated Recurrent Units (GRU) are used for each task. We posit the usage of MLB (Multimodal Low-rank Bilinear Attention Network) fusion for improvement in performance of intent and slot learning. To the best of our knowledge, this is the first attempt of using such a technique on text based problems. Also, our proposed methods outperform the existing state-of-the-

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keybhasin2020parallel

Related papers

• A Novel Bi-directional Interrelated Model For Joint Intent Detection And Slot Filling (2019)12.33
• Joint Online Spoken Language Understanding And Language Modeling With Recurrent Neural Networks (2016)13.28
• AGIF: An Adaptive Graph-interactive Framework For Joint Multiple Intent Detection And Slot Filling (2020)14.11
• Intent Recognition And Unsupervised Slot Identification For Low Resourced Spoken Dialog Systems (2021)2.26
• Sequential End-to-end Intent And Slot Label Classification And Localization (2021)3.58
• Cm-net: A Novel Collaborative Memory Network For Spoken Language Understanding (2019)13.28
• PIN: A Novel Parallel Interactive Network For Spoken Language Understanding (2020)8.09
• Improving Slot Filling By Utilizing Contextual Information (2019)2.26