JointGoalAccuracy

AbstractA typical conversation comprises of multiple turns between participants where they go back and forth between different topics. At each user turn, dialogue state tracking (DST) aims to estimate user’s …...

AbstractOver-dependence on domain ontology and lack of sharing knowledge across domains are two practical and yet less studied problems of dialogue state tracking. Existing approaches generally fall short when tracking …...

AbstractRecent works in dialogue state tracking (DST) focus on an open vocabulary-based setting to resolve scalability and generalization issues of the predefined ontology-based approaches. However, they are inefficient in that …...

AbstractIn this paper, we propose a meta-learning based semi-supervised explicit dialogue state tracker (SEDST) for neural dialogue generation, denoted as MEDST. Our main motivation is to further bridge the chasm …...

AbstractRecent progress in task-oriented neural dialogue systems is largely focused on a handful of languages, as annotation of training data is tedious and expensive. Machine translation has been used to …...

AbstractDialogue state tracking (DST), which estimates user goals given a dialogue context, is an essential component of task-oriented dialogue systems. Conventional DST models are usually trained offline, which requires a …...

AbstractWe propose NeuralWOZ, a novel dialogue collection framework that uses model-based dialogue simulation. NeuralWOZ has two pipelined models, Collector and Labeler. Collector generates dialogues from (1) user’s goal instructions, which …...

AbstractDialog State Tracking (DST), an integral part of modern dialog systems, aims to track user preferences and constraints (slots) in task-oriented dialogs. In real-world settings with constantly changing services, DST …...

AbstractThe MultiWOZ 2.0 dataset has greatly boosted the research on dialogue state tracking (DST). However, substantial noise has been discovered in its state annotations. Such noise brings about huge challenges …...

AbstractRecently proposed dialogue state tracking (DST) approaches predict the dialogue state of a target turn sequentially based on the previous dialogue state. During the training time, the ground-truth previous dialogue …...

AbstractExisting dialogue datasets contain lots of noise in their state annotations. Such noise can hurt model training and ultimately lead to poor generalization performance. A general framework named ASSIST has …...

AbstractDespite the recent advances in dialogue state tracking (DST), the joint goal accuracy (JGA) of the existing methods on MultiWOZ 2.1 still remains merely 60%. In our preliminary error analysis, …...

AbstractRobust state tracking for task-oriented dialogue systems currently remains restricted to a few popular languages. This paper shows that given a large-scale dialogue data set in one language, we can …...

AbstractThe schema-guided paradigm overcomes scalability issues inherent in building task-oriented dialogue (TOD) agents with static ontologies. Rather than operating on dialogue context alone, agents have access to hierarchical schemas containing …...