AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
To overcome the limitation of existing models, we present novel Parallel Interactive Networks for more accurate and robust dialogue state generation

Parallel Interactive Networks for Multi Domain Dialogue State Generation

EMNLP 2020, pp.1921-1931, (2020)

Cited by: 0|Views228
Full Text
Bibtex
Weibo

Abstract

The dependencies between system and user utterances in the same turn and across different turns are not fully considered in existing multidomain dialogue state tracking (MDST) models. In this study, we argue that the incorporation of these dependencies is crucial for the design of MDST and propose Parallel Interactive Networks (PIN) to mo...More

Code:

Data:

0
Introduction
  • Spoken dialogue system (SDS) is an application that can help users complete their goals efficiently.
  • Several models have been proposed for MDST task and proven to be successful (Mrksic et al, 2015; Ramadan et al, 2018; Goel et al, 2019; Eric et al, 2019; Lee et al, 2019; Wu et al, 2019)
  • Among these models, TRADE (Wu et al, 2019) achieves the state-of-the-art on the MultiWOZ 2.0 dataset by encoding the entire dialogue history using a bidirectional GRU and incorporating soft-gated copy mechanism to generate the values.
  • This observation inspires the designing of the distributed copy mechanism which allows the state generator choosing to copy words from either the historical system utterances or the historical user utterances
Highlights
  • Spoken dialogue system (SDS) is an application that can help users complete their goals efficiently
  • This paper studies the problem of state generation for multi-domain dialogues
  • To overcome the limitation of existing models, we present novel Parallel Interactive Networks (PIN) for more accurate and robust dialogue state generation
  • The design of the PIN model is inspired by the interactive nature of the dialogues and the overlapping slots in the ontology
  • The cross-turn dependencies and the in-turn dependencies are characterized by the Interactive Encoder
  • Empirical studies on two benchmark datasets demonstrate the effectiveness of the PIN model
Methods
  • The authors introduce the proposed PIN model.
  • The model consists of four components: Interactive Encoder, Slot-level Context, Value Generator and Slot Gate.
  • The authors' design of the Interactive Encoder is inspired by the dependencies between the system and user utterances.
  • The authors wish to propose a novel network structure that completely represents the dependencies expressed in Figure 1.
  • A hierarchical recurrent networks with specific structures has been used to construct the Interactive Encoder, as shown in Figure 2.
Results
  • Evaluation on the MultiWOZ 2.0 dataset.
  • The evaluation results on the MultiWOZ 2.0 dataset are shown in Table 1.
  • The authors observe from the table that most of the models building classifiers on predefined ontology and the models generating the Model.
  • Joint Goal (%) Goal (%).
  • MDBT PtrNet GLAD GCE HJST DSTreader FJST HyST HyST(ensemble) SUMBT DSTreader+JST TRADE PIN
Conclusion
  • This paper studies the problem of state generation for multi-domain dialogues.
  • Existing generationbased models fail to model the dialogue dependencies and ignore the slot-overlapping problem in MDST.
  • To overcome the limitation of existing models, the authors present novel Parallel Interactive Networks (PIN) for more accurate and robust dialogue state generation.
  • The design of the PIN model is inspired by the interactive nature of the dialogues and the overlapping slots in the ontology.
  • The slot-overlapping problem are solved by introducing the slot-level context.
  • Empirical studies on two benchmark datasets demonstrate the effectiveness of the PIN model
Summary
  • Introduction:

    Spoken dialogue system (SDS) is an application that can help users complete their goals efficiently.
  • Several models have been proposed for MDST task and proven to be successful (Mrksic et al, 2015; Ramadan et al, 2018; Goel et al, 2019; Eric et al, 2019; Lee et al, 2019; Wu et al, 2019)
  • Among these models, TRADE (Wu et al, 2019) achieves the state-of-the-art on the MultiWOZ 2.0 dataset by encoding the entire dialogue history using a bidirectional GRU and incorporating soft-gated copy mechanism to generate the values.
  • This observation inspires the designing of the distributed copy mechanism which allows the state generator choosing to copy words from either the historical system utterances or the historical user utterances
  • Methods:

    The authors introduce the proposed PIN model.
  • The model consists of four components: Interactive Encoder, Slot-level Context, Value Generator and Slot Gate.
  • The authors' design of the Interactive Encoder is inspired by the dependencies between the system and user utterances.
  • The authors wish to propose a novel network structure that completely represents the dependencies expressed in Figure 1.
  • A hierarchical recurrent networks with specific structures has been used to construct the Interactive Encoder, as shown in Figure 2.
  • Results:

    Evaluation on the MultiWOZ 2.0 dataset.
  • The evaluation results on the MultiWOZ 2.0 dataset are shown in Table 1.
  • The authors observe from the table that most of the models building classifiers on predefined ontology and the models generating the Model.
  • Joint Goal (%) Goal (%).
  • MDBT PtrNet GLAD GCE HJST DSTreader FJST HyST HyST(ensemble) SUMBT DSTreader+JST TRADE PIN
  • Conclusion:

    This paper studies the problem of state generation for multi-domain dialogues.
  • Existing generationbased models fail to model the dialogue dependencies and ignore the slot-overlapping problem in MDST.
  • To overcome the limitation of existing models, the authors present novel Parallel Interactive Networks (PIN) for more accurate and robust dialogue state generation.
  • The design of the PIN model is inspired by the interactive nature of the dialogues and the overlapping slots in the ontology.
  • The slot-overlapping problem are solved by introducing the slot-level context.
  • Empirical studies on two benchmark datasets demonstrate the effectiveness of the PIN model
Tables
  • Table1: Evaluation on the MultiWOZ 2.0 dataset
  • Table2: Evaluation on the MultiWOZ 2.1 dataset
  • Table3: The evaluation results for overlapping slots on the MultiWOZ 2.1 dataset. The involved domains are 1:Restaurant, 2:Hotel, 3:Attraction, 4:Train, 5:Taxi
Download tables as Excel
Related work
  • The dialogue state tracking (DST) problem has attracted the research community for years. The traditional single domain dialogue state tracking that focus on predicting dialogue states on specific domain has been studied intensively and achieve remarkable success (Thomson and Young, 2010; Wang and Lemon, 2013; Lee and Kim, 2016; Liu and Perez, 2017; Jang et al, 2016; Shi et al, 2016; Vodolan et al, 2017; Yu et al, 2015; Henderson et al, 2014; Zilka and Jurcıcek, 2015; Mrksic et al, 2017; Xu and Hu, 2018; Zhong et al, 2018; Ren et al, 2018). Some of these models solve DST problem by incorporating a natural language understanding (NLU) module (Thomson and Young, 2010; Wang and Lemon, 2013) or jointly modeling NLU and DST (Henderson et al, 2014; Zilka and Jurcıcek, 2015). These models rely on hand-crafted features or delexicalisation features, which make them difficult to scale to realistic applications. The representation learning approach has then been employed in NBT (Mrksic et al, 2017). Following representation learning approach, the GLAD (Zhong et al, 2018) utilizes the recurrent neural networks (RNN) and the self-attention to handle rare-slot-value problem. And the StateNet (Ren et al, 2018) model propose a multi-scale receptors to extract semantic features and use LSTM for state tracking. The generation-based approach for dialogue state tracking is first adopted in PtrNet (Xu and Hu, 2018) for handling the unknown-value problem. It utilize the Pointer networks (Vinyals and Le, 2015) to predict the indexes of the value sequence.
Reference
  • Samuel R. Bowman, Luke Vilnis, Oriol Vinyals, Andrew M. Dai, Rafal Jozefowicz, and Samy Bengio. 2016. Generating sentences from a continuous space. In Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning, CoNLL 2016, Berlin, Germany, August 11-12, 2016, pages 10–21.
    Google ScholarLocate open access versionFindings
  • Pawel Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, Inigo Casanueva, Stefan Ultes, Osman Ramadan, and Milica Gasic. 2018. Multiwoz - A largescale multi-domain wizard-of-oz dataset for taskoriented dialogue modelling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, October 31 - November 4, 2018, pages 5016–5026.
    Google ScholarLocate open access versionFindings
Your rating :
0

 

Tags
Comments
小科