A Simple and Generic Belief Tracking Mechanism for the Dialog State Tracking Challenge: On the believability of observed information

By Zhuoran Wang, Oliver Lemon. 2013

179 citations recorded by the source corpus.

How researchers see this paper

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

In Dialogue & Conversational AI

Citations in the corpus

Learning End-to-End Goal-Oriented Dialog (2016, methodology): “…for a single domain and rely heavily on expert knowledge; for instance, most of these systems, called slot-ﬁlling methods (Lemon et al. , 2006; Wang and Lemon, 2013), require to predeﬁne the structure of the dialog state as a form composed of a set of slots to be ﬁlled during the dialog.”
A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version (2015, background): “, 2000), dialogue state tracking (Thomson and Young, 2010; Wang and Lemon, 2013; Ren et al., 2013; Henderson et al., 2013; Williams et al., 2013; Henderson et al., 2014c; Kim et al., 2015), natural language generation (Langkilde and Knight, 1998; Oh and Rudnicky, 2000; Walker et al.”
The Second Dialog State Tracking Challenge (2014, methodology): “…the rule: P ( s = v ) t = q t P ( s = v ) t − 1 + SLU ( s = v ) t where 0 ≤ SLU ( s = v ) t ≤ 1 is the evidence for s = v given by the SLU in turn t , and P Another baseline tracker, based on the tracker presented in Wang and Lemon (2013) is included in the evaluation, labelled ‘team0.entry2’.”
Multi-domain Dialog State Tracking using Recurrent Neural Networks (2015, background): “…et al., 2013; Henderson et al., 2014a; Henderson et al., 2014b) saw a variety of novel approaches, including robust sets of hand-crafted rules (Wang and Lemon, 2013), conditional random ﬁelds (Lee and Eskenazi, 2013; Lee, 2013; Ren et al., 2013), maximum entropy models (Williams, 2013) and…”
Neural Belief Tracker: Data-Driven Dialogue State Tracking (2016, methodology): “The downstream DST model then combines this information with the past dialogue context to update the belief state (Thomson and Young, 2010; Wang and Lemon, 2013; Lee and Kim, 2016; Perez, 2016; Perez and Liu, 2017; Sun et al., 2016; Jang et al., 2016; Shi et al., 2016; Dernoncourt et al., 2016; Liu ”
A Survey on Dialogue Systems: Recent Advances and New Frontiers (2017, background): “king Challenge (DSTC) [87; 86], the results are in the form of a probability distribution over each slot for each turn. A variety of statistical approaches, including robust sets of handcrafted rules [80], conditional random ﬁelds [28; 27; 53], maximum entropy models [85] and web-style ranking [88] ”
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”
The third Dialog State Tracking Challenge (2014, methodology): “These are based on the tracker presented in [14], and use a selection of domain independent rules to update the beliefs, similar to the focus baseline.”
Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering (2019, methodology): “Early models of dialogue state tracking (Thomson & Young, 2010; Wang & Lemon, 2013; Henderson et al., 2014) rely on handcrafted features to extract utterance semantics, and then use these features to predict dialogue states.”
Multi-task Learning for Joint Language Understanding and Dialogue State Tracking (2018, background): “ing models have ranged from rule-based (Wang and Lemon, 2013), to generative (Thomson and Young, 2010), discriminative (Henderson et al.”
Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking (2020, background): “Previous works on DST use different approaches, ranging from using handcrafted features to elicit utterance information (Henderson et al., 2014; Wang and Lemon, 2013).”
The Dialog State Tracking Challenge Series: A Review (2016, methodology): “Reference Description team1 entry1 (Henderson et al., 2013) Deep neural network team2 entry1 (Wang and Lemon, 2013) Hand-crafted rules based on conﬁdence scores team3 entry2 (Zilka et al., 2013) Discriminative classiﬁer + hand-crafted transition probabilities team4 entry1 (anonymous) Discriminative ”
What Should I Ask? Using Conversationally Informative Rewards for Goal-oriented Visual Dialog. (2019, unknown): “Most earlier works made use of a predefined template (Lemon et al., 2006; Wang and Lemon, 2013) to generate dialogues.”
Learning Domain-Independent Dialogue Policies via Ontology Parameterisation (2015, methodology): “…for SDS include domain-independent intermediate semantic extractors for Spoken Language Understanding (SLU) (Li et al., 2014), domain-general rules (Wang and Lemon, 2013; Sun et al., 2014) and delexicalised deep classiﬁers (Henderson et al., 2014; Mrkˇsi´c et al., 2015) for dialogue state…”