An approach to intent detection and classification based on attentive recurrent neural networks

Intent Detection is a key component of any task-oriented conversational system. To understand the user’s current goal and provide the most adequate response, the system must leverage its intent detector to classify the user’s utterance into one of several predefined classes (intents). This objective can also simplify the set of processes that a conversational system must complete by performing the natural language understanding and dialog management tasks into a single process conducted by the intent detector. This is particularly useful for systems oriented to FAQ services. In this paper we present a novel approach for intent detection and classification based on word-embeddings and recurrent neural networks. We have validated our approach with a selection of the corpus acquired with the Hispabot-Covid19 system obtaining satisfactory results.

[1]  Bing Liu,et al.  Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling , 2016, INTERSPEECH.

[2]  John Pavlopoulos,et al.  Deep Learning for User Comment Moderation , 2017, ALW@ACL.

[3]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[4]  Tianyong Hao,et al.  A Feature-Enriched Method for User Intent Classification by Leveraging Semantic Tag Expansion , 2018, NLPCC.

[5]  Minho Lee,et al.  Human implicit intent recognition based on the phase synchrony of EEG signals , 2015, Pattern Recognit. Lett..

[6]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[7]  Benjamin Roth,et al.  Intent Recognition in Doctor-Patient Interviews , 2020, LREC.

[8]  Prakhar Gupta,et al.  Learning Word Vectors for 157 Languages , 2018, LREC.

[9]  Andreas Stolcke,et al.  A comparative study of neural network models for lexical intent classification , 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

[10]  K Sreelakshmi,et al.  Deep Bi-Directional LSTM Network for Query Intent Detection , 2018 .

[11]  Homa B. Hashemi,et al.  Query Intent Detection using Convolutional Neural Networks , 2016 .

[12]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.

[13]  Shrikanth Narayanan,et al.  NTUA-SLP at SemEval-2018 Task 1: Predicting Affective Content in Tweets with Deep Attentive RNNs and Transfer Learning , 2018, *SEMEVAL.

[14]  Lingjia Tang,et al.  An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction , 2019, EMNLP.

[15]  David Griol,et al.  The Conversational Interface: Talking to Smart Devices , 2016 .

[16]  Dilek Z. Hakkani-Tür,et al.  Easy contextual intent prediction and slot detection , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[17]  Asif Ekbal,et al.  A Deep Multi-task Model for Dialogue Act Classification, Intent Detection and Slot Filling , 2020, Cognitive Computation.

[18]  Min Lin,et al.  Review of Intent Detection Methods in the Human-Machine Dialogue System , 2019, Journal of Physics: Conference Series.

[19]  Tomas Mikolov,et al.  Advances in Pre-Training Distributed Word Representations , 2017, LREC.

[20]  Naphtali Rishe,et al.  Sentiment Analysis Using Dependency Trees and Named-Entities , 2014, FLAIRS Conference.

[21]  Michael F. McTear,et al.  Conversational AI: Dialogue Systems, Conversational Agents, and Chatbots , 2020, Conversational AI.

[22]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[23]  Philip S. Yu,et al.  Zero-shot User Intent Detection via Capsule Neural Networks , 2018, EMNLP.

[24]  Gökhan Tür,et al.  Intent detection using semantically enriched word embeddings , 2016, 2016 IEEE Spoken Language Technology Workshop (SLT).