An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking

By Puyang Xu, Qi Hu. 2018

128 citations recorded by the source corpus.

We highlight a practical yet rarely discussed problem in dialogue state tracking (DST), namely handling unknown slot values. Previous approaches generally assume predefined candidate lists and thus are not designed to output unknown values, especially when the spoken language understanding (SLU) module is absent as in many end-to-end (E2E) systems. We describe in this paper an E2E architecture based on the pointer network (PtrNet) that can effectively extract unknown slot values while still obtains state-of-the-art accuracy on the standard DSTC2 benchmark. We also provide extensive empirical evidence to show that tracking unknown values can be challenging and our approach can bring significant improvement with the help of an effective feature dropout technique.

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

Continual Prompt Tuning for Dialog State Tracking (2022, background): “To alleviate the reliance on the ontology and improve generalization to unseen values, some work extract values from a dialog context (Xu and Hu, 2018; Gao et al., 2019) while others generate values directly to handle situations where values are missing from the context (Wu et al.”
Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems (2019, background): “SpanPtr (Xu and Hu, 2018), and we briefly describe these baselines models below:”
MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines (2020, background): “…the locations in the user and system utterances where slot values have been mentioned, to make the system efﬁcient and generalizable to new slot values (Rastogi et al., 2017; Wu et al., 2019; Zhang et al., 2019; Rastogi et al., 2019; Xu and Hu, 2018; Zhou and Small, 2019; Gao et al., 2019).”
Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking (2020, background): “Xu and Hu (2018) use a pointer network with a Seq2Seq architecture to handle unseen slot values.”
Data Augmentation with Atomic Templates for Spoken Language Understanding (2019, methodology): “The pointer softmax (Gulcehre et al., 2016) enhanced by a trick of targeted feature dropout (Xu and Hu, 2018) is adopted to tackle OOV words, which will switch between generation and copying from the input source dynamically.”
Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking (2019, methodology): “We follow recent strategies [25, 27] to predict the values for all the domainslot pairs in S at each turn.”
Data Augmentation for Copy-Mechanism in Dialogue State Tracking (2020, unknown): “To reduce the dependence on the ontology, PtrNet [ Xu and Hu, 2018 ] uses the Pointer Network [ Vinyals et al. , 2015 ] to handle the unknown values that are not deﬁned in the ontology, since then the attention-based copy-mechanism inspired by Pointer Network become widely used in state-of-the-art…”
Toward Scalable Neural Dialogue State Tracking Model (2018, background): “Recently, Xu and Hu (2018) proposed a model for unknown slot type by using a pointer network, based on conditioning to slot type embedding.”
Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks (2020, background): “Recently, most works about DST focus on encoding dialogue context with deep neural networks (such as CNN, RNN, LSTM-RNN, etc.) and predicting a value for each possible slot (Mrkˇsi´c et al. 2017; Xu and Hu 2018; Zhong, Xiong, and Socher 2018; Ren et al. 2018; Xie et al. 2018).”
Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering (2019, background): “Xu & Hu (2018) propose to use a pointer network with a Seq2Seq architecture to handle unseen slot values.”
Dialog State Tracking: A Neural Reading Comprehension Approach (2019, methodology): “Perhaps, the most similar technique to our work is the pointer networks proposed by Xu and Hu (2018) wherein an attention-based mechanism is employed to point the start and end token of a slot value.”
TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking (2020, background): “For instance, Xu and Hu (2018) utilizes an attention-based recurrent network with a pointer mechanism to extract values from the context.”