Multi-task Learning for Joint Language Understanding and Dialogue State Tracking

By Abhinav Rastogi, Raghav Gupta, Dilek Z. Hakkani-Tür. 2018

57 citations recorded by the source corpus.

This paper presents a novel approach for multi-task learning of language understanding (LU) and dialogue state tracking (DST) in task-oriented dialogue systems. Multi-task training enables the sharing of the neural network layers responsible for encoding the user utterance for both LU and DST and improves performance while reducing the number of network parameters. In our proposed framework, DST operates on a set of candidate values for each slot that has been mentioned so far. These candidate sets are generated using LU slot annotations for the current user utterance, dialogue acts corresponding to the preceding system utterance and the dialogue state estimated for the previous turn, enabling DST to handle slots with a large or unbounded set of possible values and deal with slot values not seen during training. Furthermore, to bridge the gap between training and inference, we investigate the use of scheduled sampling on LU output for the current user utterance as well as the DST output for the preceding turn.

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

Dynamic Dialogue Policy for Continual Reinforcement Learning (2022, background): “In dialogue state tracking we often observe that similarity matching approaches predict values they already know when faced with new unseen values, which leads to poor zero-shot generalisation (Rastogi et al., 2018).”
Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset (2019, background): “Addressing these concerns, approaches utilizing a dynamic vocabulary of slot values have been proposed (Rastogi, Gupta, and Hakkani-Tur 2018; Goel, Paul, and Hakkani-T¨ur 2019; Wu et al. 2019).”
Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat (2018, unknown): “Recent works combine conventional symbolic with neural approaches (Williams et al., 2017; Zhao and Eskenazi, 2016; Rastogi et al., 2018), but all focus on language-only dialogue.”
Dynamic Dialogue Policy Transformer for Continual Reinforcement Learning (2022, background): “logue state tracking we often observe that similarity matching approaches predict values they already know when faced with new unseen values, which leads to poor zero-shot generalisation (Rastogi et al., 2018).”