The third Dialog State Tracking Challenge

By Matthew Henderson, Blaise Thomson, Jason Williams. 2014

182 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Evaluation & Benchmarks

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

In Evaluation & Benchmarks

Citations in the corpus

Towards Exploiting Background Knowledge for Building Conversation Systems (2018, background): “Some of these datasets contain transcripts of human-bot conversations (Williams et al., 2013; Henderson et al., 2014a,b) while others are created using a ﬁxed set of natural language patterns (Bordes and Weston, 2017; Dodge et al., 2016).”
Neural Approaches to Conversational AI (2018, neutral): “(2013), it has successfully attracted many research teams to focus on a wide range of technical problems in DST (Williams et al., 2014; Henderson et al., 2014b; Henderson et al., 2014a; Kim et al., 2016a; Kim et al., 2016b; Hori et al., 2017).”
An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction (2019, background): “, 2014a), and DSTC 3 (Henderson et al., 2014b) contain “chatbot style” queries, but the datasets are focused on state tracking.”
MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling (2018, methodology): “This is in contrast to previous approaches (Henderson et al., 2014a) and such WOZ set-up has been successfully validated by Wen et al. (2017) and Asri et al. (2017).”
Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset (2019, background): “The Dialogue State Tracking Challenges (Williams et al. 2013; Henderson, Thomson, and Williams 2014a; 2014b; Kim et al. 2017) contributed to the creation of dialogue datasets with increasing complexity.”
Frames: a corpus for adding memory to goal-oriented dialogue systems (2017, methodology): “This requires, e.g. , a natural language understanding module that already performs well on the task, which implies possession of in-domain data or the ability to generate it (Henderson et al., 2014b; Raux et al., 2003).”
Domain Adaptive Dialog Generation via Meta Learning (2019, background): “, dialog state tracker (Henderson et al., 2014), dialog policy learning (Cuay´ahuitl et al., 2015; Young et al., 2013) and natural language generation (NLG) (Dhingra et al., 2017; Wen et al., 2015).”
Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking (2019, background): “ates in complicated conversations across multiple domains with many slots. It has been a hot research topic during the past few years, along with the development of Dialogue State Tracking Challenges [24, 9, 10, 13, 12, 21]. Traditional approaches usually rely on handcrafted features or domain-speci”
Data Augmentation for Copy-Mechanism in Dialogue State Tracking (2020, unknown): “Deep-learning has recently shown its power to the dialogue state tracking challenges [ Williams et al. , 2013; Henderson et al. , 2014a; Henderson et al. , 2014b ] .”
ConveRT: Efficient and Accurate Conversational Representations from Transformers (2019, background): “They mitigate the requirements for explicit task-specific semantics hand-crafted by domain experts (Henderson et al., 2014; Mrkšić et al., 2015, 2017). large collection of responses in a joint semantic space, and then retrieve the most relevant response by matching the query representation…”
Dialog System Technology Challenge 7 (2019, background): “Such end-to-end approaches have been shown to better handle flexible conversations by enabling model training on large conversational datasets Vinyals and Le [2015], Hori et al. [2018b]. However, current dialog systems cannot understand a scene and have a conversation about what is going on in it.”
Recent advances in deep learning based dialogue systems: a systematic survey (2021, methodology): “Some dialogue systems took the output of the NLU module as the input of DST module (Williams et al., 2013; Henderson et al., 2014a,b), while others directly used raw user messages to track the state (Kim et al., 2019; Wang et al., 2020e; Hu et al., 2020).”
Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks (2020, background): “…rely on semantics extracted by natural language understanding to predict the current dialogue states (Young et al. 2013; Williams et al. 2013; Henderson, Thomson, and Williams 2014b; Yu et al. 2015; Sun et al. 2014b; 2014a; Xie et al. 2015; Yu et al. 2016), or jointly learn language…”
Few-Shot Dialogue Generation Without Annotated Data: A Transfer Learning Approach (2019, background): “There is a substantial amount of work on learning dialogue with minimal data — starting with the Dialog State Tracking Challenge 3 (Henderson et al., 2014) where the problem was to adjust a pre-trained state tracker to a different domain using a seed dataset.”