Incremental LSTM-based dialog state tracker

By Lukás Zilka, Filip Jurcícek. 2015

72 citations recorded by the source corpus.

A dialog state tracker is an important component in modern spoken dialog systems. We present an incremental dialog state tracker, based on LSTM networks. It directly uses automatic speech recognition hypotheses to track the state. We also present the key non-standard aspects of the model that bring its performance close to the state-of-the-art and experimentally analyze their contribution: including the ASR confidence scores, abstracting scarcely represented values, including transcriptions in the training data, and model averaging.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Neural Belief Tracker: Data-Driven Dialogue State Tracking (2016, methodology): “To perform belief tracking, the shared model iterates over all slot-value pairs, extracting delexicalised feature vectors and making a separate binary decision regarding each pair.”
Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems (2019, background): “Dialogue State Tracking Traditional dialogue state tracking models combine semantics extracted by language understanding modules to estimate the current dialogue states (Williams and Young, 2007; Thomson and Young, 2010; Wang and Lemon, 2013; Williams, 2014), or to jointly learn speech understanding”
Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking (2019, background): “conversational turns. Fig. 1 shows a dialogue with correspondingannotatedturn states. Traditional approaches for DST usually rely on hand-crafted features and domain-speciﬁc lexicon (besides ontology)[11, 30, 23, 18]. Recent data-drivendeeplearningmodelshaveshownpromising performancesinDST[27,25,14,”
Incorporating Unstructured Textual Knowledge Sources into Neural Dialogue Systems (2015, background): “Recent work incorporates neural networks in order to improve the performance of these models for state tracking [7, 22], speech recognition [4, 5], and natural language generation [19].”
Machine Learning for Dialog State Tracking: A Review (2015, methodology): “Long Short-Term Memory (LSTM) networks [42] have also been applied to the task of word-based DST, modeling not only the sequence of turns, but also the sequence of words within a turn [43].”
An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking (2018, methodology): “joint modeling of SLU and DST has also been presented in the literature (Henderson et al., 2014b,c; Mrksic et al., 2015; Zilka and Jurcicek, 2015; Perez and Liu, 2017; Mrksic et al., 2017).”