Multi-domain Dialog State Tracking using Recurrent Neural Networks
By Nikola Mrksic, Diarmuid Ó Séaghdha, Blaise Thomson, Milica Gasic, Pei-hao Su, David Vandyke, Tsung-Hsien Wen, Susannah Young. 2015
189 citations recorded by the source corpus.
Dialog state tracking is a key component of many modern dialog systems, most of which are designed with a single, well-defined domain in mind. This paper shows that dialog data drawn from different dialog domains can be used to train a general belief tracking model which can operate across all of these domains, exhibiting superior performance to each of the domain-specific models. We propose a training procedure which uses out-of-domain data to initialise belief tracking models for entirely new domains. This procedure leads to improvements in belief tracking performance regardless of the amount of in-domain data available for training the model.
Subfields: Artificial Intelligence, Model Architectures, Dialogue & Conversational AI
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
- Jianfeng Gao
- Richard Socher
- Caiming Xiong
- Mohit Bansal
- Percy Liang
- Jason Aaron Edward Weston
- Luke S. Zettlemoyer
- Yoshua Bengio
In Model Architectures
- Richard Socher
- Caiming Xiong
- Lina Maria Rojas-Barahona
- Dilek Z. Hakkani-Tür
- Xi Victoria Lin
- Kun Qian
- Rui Zhang
- Tsung-Hsien Wen
In Dialogue & Conversational AI
- Susannah Young
- Milica Gasic
- Pei-hao Su
- Tsung-Hsien Wen
- Blaise Thomson
- Matthew Henderson
- Nikola Mrksic
- Stefan Ultes
Citations in the corpus
- Neural Approaches to Conversational AI (2018, neutral): “, 2013) and recurrent networks (Mrkšić et al., 2015) as some of the early examples.”
- Generative Deep Neural Networks for Dialogue: A Short Review (2016, background): “…investigated applying neural networks to the different components of a standard dialogue system, including natural language understanding, natural language generation, dialogue state tracking and evaluation [Wen et al., 2016, 2015, Henderson et al., 2013, Mrkši´c et al., 2015, Su et al., 2015].”
- Continuously Learning Neural Dialogue Management (2016, background): “As depicted in Figure 1, the input to the model is the belief state s which encodes the understood user in-tents along with the dialogue history (Henderson et al., 2014b; Mrkˇsi´c et al., 2015), and the output is the master dialogue action a that decides the semantic reply.”
- Neural Belief Tracker: Data-Driven Dialogue State Tracking (2016, neutral): “As shown by Mrkˇsi´c et al. (2015), such parameter tying can facilitate transfer learning and lead to improved belief tracking performance.”
- Look Before you Speak: Visually Contextualized Utterances (2020, background): “Most traditional conversational datasets [6, 10, 31, 71] are solely text based, and notoriously difficult to collect, relying on narrowly constructed ontologies [31, 55] and highly specific domains [6, 10].”
- Domain Adaptive Dialog Generation via Meta Learning (2019, background): “Some domain adaptation work has been done on dialog states tracking (Mrkˇsi´c et al., 2015) and dialog policy learning (Vlasov et al., 2018) as well.”
- Learning Domain-Independent Dialogue Policies via Ontology Parameterisation (2015, background): “…(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 tracking, and domain-extensible/transferable statistical dialogue policies (Lemon et al., 2006; Gaˇsi´c et…”
- 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…”
- CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases (2019, background): “…dialogue settings by virtue of continuous effort of corpus creation (Seneff and Polifroni, 2000; Walker et al., 2002; Raux et al., 2005; Mrksic et al., 2015; Asri et al., 2017; Budzianowski et al., 2018) and modelling innovation (Artzi and Zettlemoyer, 2011; Henderson et al., 2013; Lee…”
- Adversarial Domain Adaptation for Variational Neural Language Generation in Dialogue Systems (2018, background): “Mrkšić et al. (2015) addressed the question of multi-domain in the SDS belief tracking by training a general model and adapting it to each domain.”