0% Complete
Home
/
12th International Conference on Computer and Knowledge Engineering
Span-prediction of Unknown Values for Long-sequence Dialogue State Tracking
Authors :
Marzieh Naghdi Dorabati
1
Reza Ramezani
2
Mohammad Ali Nematbakhsh
3
1- Department of Computer Engineering, University of Isfahan
2- Dept. of Computer Engineering, University of Isfahan
3- Dept. of Computer Engineering, University of Isfahan
Keywords :
Task-oriented Dialogue Systems،Dialogue State Tracking،Unknown Values،Diversity of User Utterances،Long Sequences
Abstract :
Abstract—Dialogue state tracking is one of the main components in task-oriented dialogue systems whose duty is tracking the user goal during the conversation. Due to the diversity in natural languages and existing different utterances, the user requests may include unknown values at different turns in these systems. However, predicting true values of the user requests is necessary for completing the intended task. In existing studies, these values are determined using span-based methods to predict a span in utterances or previous dialogues. However, the slots are not correctly filled when values are multi-word. In addition, in some scenarios, the slot values in a given turn may depend on previously dialogue states. However, due to the limitation of the input length of language models, it is impossible to access all the previous dialogue states. In this study, a new approach is proposed that uses a span-tokenizer and adds the Bi-LSTM layer on top of the BERT model to predict the exact span of multi-word values. This approach uses parameters like user utterance, important dialogue histories, and all dialogue states as input to decrease the length of the sequences. The results show that this strategy has led to 1.80% improvement in the joint-goal accuracy and 0.15% improvement in the slot accuracy metrics over the MultiWOZ 2.1 dataset compared to the SAVN model.
Papers List
List of archived papers
Joint ADC-less Analog Demodulator and Decoder for Extended Binary (8, 4, 4) Hamming Channel Code
Mir Mahdi Safari - Jafar Pourrostam - Behzad Mozaffari Tazehkand
Ramp Progressive Secret Image Sharing using Ensemble of Simple Methods
Atieh Mokhtari - Mohammad Taheri
Cross-project Defect Prediction with An Enhanced Transfer Boosting Algorithm
Nazgol Nikravesh - Mohammad Reza Keyvanpour
A New Time Series Approach in Churn Prediction with Discriminatory Intervals
Hedieh Ahmadi - Seyed Mohammad Hossein Hasheminejad
Community-Based QoE Enhancement for User-Generated Content Live Streaming
Reza Saeedinia - S.Omid Fatemi - Daniele Lorenzi - Farzad Tashtarian - Christian Timmerer
EfficientNetB0’s Hybrid Approach for Brain Tumor Classification from MRI Images Using Deep Learning and Bagging Trees
Yeganeh Modaresnia - Farhad Abedinzadeh Torghabeh - Seyyed Abed Hosseini
Emotion Recognition In Persian Speech Using Deep Neural Networks
Ali Yazdani - Hossein Simchi - Yasser Shekofteh
Speech Emotion Recognition Using a Hierarchical Adaptive Weighted Multi-Layer Sparse Auto-Encoder Extreme Learning Machine with New Weighting and Spectral/SpectroTemporal Gabor Filter Bank Features
Fatemeh Daneshfar - Seyed Jahanshah Kabudian
Distilled BERT Model In Natural Language Processing
Yazdan Zandiye Vakili - Avisa Fallah - Hedieh Sajedi
Multi-Task Transformer for Stock Market Trend Prediction
Seyed Morteza Mirjebreili - Ata Solouki - Hamidreza Soltanalizadeh - Mohammad Sabokrou
more
Samin Hamayesh - Version 41.5.3