Browse > Natural Language Processing > Dialogue > Dialogue State Tracking

Dialogue State Tracking

12 papers with code · Natural Language Processing
Subtask of Dialogue

Dialogue state tacking consists of determining at each turn of a dialogue the full representation of what the user wants at that point in the dialogue, which contains a goal constraint, a set of requested slots, and the user's dialogue act.

State-of-the-art leaderboards

Greatest papers with code

Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems

HLT 2018 google-research-datasets/simulated-dialogue

Popular methods for learning task-oriented dialogues include applying reinforcement learning with user feedback on supervised pre-training models. To address this challenge, we propose a hybrid imitation and reinforcement learning method, with which a dialogue agent can effectively learn from its interaction with users by learning from human teaching and feedback.

DIALOGUE STATE TRACKING IMITATION LEARNING TASK-ORIENTED DIALOGUE SYSTEMS

Scalable Multi-Domain Dialogue State Tracking

29 Dec 2017google-research-datasets/simulated-dialogue

State of the art approaches for state tracking rely on deep learning methods, and represent dialogue state as a distribution over all possible slot values for each slot present in the ontology. We introduce a novel framework for state tracking which is independent of the slot value set, and represent the dialogue state as a distribution over a set of values of interest (candidate set) derived from the dialogue history or knowledge.

DIALOGUE STATE TRACKING TASK-ORIENTED DIALOGUE SYSTEMS TRANSFER LEARNING

Global-Locally Self-Attentive Dialogue State Tracker

19 May 2018salesforce/glad

Dialogue state tracking, which estimates user goals and requests given the dialogue context, is an essential part of task-oriented dialogue systems. In this paper, we propose the Global-Locally Self-Attentive Dialogue State Tracker (GLAD), which learns representations of the user utterance and previous system actions with global-local modules.

DIALOGUE STATE TRACKING TASK-ORIENTED DIALOGUE SYSTEMS

Fully Statistical Neural Belief Tracking

29 May 2018nmrksic/neural-belief-tracker

This paper proposes an improvement to the existing data-driven Neural Belief Tracking (NBT) framework for Dialogue State Tracking (DST). The existing NBT model uses a hand-crafted belief state update mechanism which involves an expensive manual retuning step whenever the model is deployed to a new dialogue domain.

DIALOGUE STATE TRACKING

Counter-fitting Word Vectors to Linguistic Constraints

HLT 2016 nmrksic/counter-fitting

In this work, we present a novel counter-fitting method which injects antonymy and synonymy constraints into vector space representations in order to improve the vectors' capability for judging semantic similarity. Applying this method to publicly available pre-trained word vectors leads to a new state of the art performance on the SimLex-999 dataset.

DIALOGUE STATE TRACKING SEMANTIC TEXTUAL SIMILARITY

Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints

1 Jun 2017nmrksic/attract-repel

We present Attract-Repel, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources. Attract-Repel facilitates the use of constraints from mono- and cross-lingual resources, yielding semantically specialised cross-lingual vector spaces.

DIALOGUE STATE TRACKING SEMANTIC TEXTUAL SIMILARITY

Explicit State Tracking with Semi-Supervision for Neural Dialogue Generation

31 Aug 2018AuCson/SEDST

However, the \emph{expensive nature of state labeling} and the \emph{weak interpretability} make the dialogue state tracking a challenging problem for both task-oriented and non-task-oriented dialogue generation: For generating responses in task-oriented dialogues, state tracking is usually learned from manually annotated corpora, where the human annotation is expensive for training; for generating responses in non-task-oriented dialogues, most of existing work neglects the explicit state tracking due to the unlimited number of dialogue states. In this paper, we propose the \emph{semi-supervised explicit dialogue state tracker} (SEDST) for neural dialogue generation.

DIALOGUE GENERATION DIALOGUE STATE TRACKING

Toward Scalable Neural Dialogue State Tracking Model

3 Dec 2018elnaaz/GCE-Model

The latency in the current neural based dialogue state tracking models prohibits them from being used efficiently for deployment in production systems, albeit their highly accurate performance. This paper proposes a new scalable and accurate neural dialogue state tracking model, based on the recently proposed Global-Local Self-Attention encoder (GLAD) model by Zhong et al. which uses global modules to share parameters between estimators for different types (called slots) of dialogue states, and uses local modules to learn slot-specific features.

DIALOGUE STATE TRACKING

Dynamic Time-Aware Attention to Speaker Roles and Contexts for Spoken Language Understanding

30 Sep 2017MiuLab/Time-SLU

Spoken language understanding (SLU) is an essential component in conversational systems. However, the previous model only paid attention to the content in history utterances without considering their temporal information and speaker roles.

DIALOGUE STATE TRACKING SPOKEN LANGUAGE UNDERSTANDING