Goal-Oriented Dialogue Systems
12 papers with code • 0 benchmarks • 4 datasets
Achieving a pre-defined goal through a dialog.
Benchmarks
These leaderboards are used to track progress in Goal-Oriented Dialogue Systems
MultiDoc2Dial
MMD
DSTC7 Task 1
Latest papers
In-Context Learning User Simulators for Task-Oriented Dialog Systems
telepathylabsai/prompt-based-user-simulator
•
•
This paper presents a novel application of large language models in user simulation for task-oriented dialog systems, specifically focusing on an in-context learning approach.
Learning Dialogue Representations from Consecutive Utterances
amazon-research/dse
•
•
NAACL 2022
In this paper, we introduce Dialogue Sentence Embedding (DSE), a self-supervised contrastive learning method that learns effective dialogue representations suitable for a wide range of dialogue tasks.
Knowledge-Driven Slot Constraints for Goal-Oriented Dialogue Systems
amazon-research/nlu-slot-constraints
•
•
NAACL 2021
Practically, some combinations of slot values can be invalid according to external knowledge.
Maintaining Common Ground in Dynamic Environments
Alab-NII/dynamic-onecommon
•
•
Common grounding is the process of creating and maintaining mutual understandings, which is a critical aspect of sophisticated human communication.
On the Robustness of Intent Classification and Slot Labeling in Goal-oriented Dialog Systems to Real-world Noise
In this work, we investigate how robust IC/SL models are to noisy data.
Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformers
SmartDataAnalytics/kgirnet
•
•
Generating knowledge grounded responses in both goal and non-goal oriented dialogue systems is an important research challenge.
Utterance-level Dialogue Understanding: An Empirical Study
Most of these approaches account for the context for effective understanding.
A Fast and Robust BERT-based Dialogue State Tracker for Schema-Guided Dialogue Dataset
NVIDIA/NeMo
•
•
Dialog State Tracking (DST) is one of the most crucial modules for goal-oriented dialogue systems.
Incorporating Joint Embeddings into Goal-Oriented Dialogues with Multi-Task Learning
Since such models can greatly benefit from user intent and knowledge graph integration, in this paper we propose an RNN-based end-to-end encoder-decoder architecture which is trained with joint embeddings of the knowledge graph and the corpus as input.
Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models
snakeztc/NeuralDialog-LaRL
•
•
NAACL 2019
Defining action spaces for conversational agents and optimizing their decision-making process with reinforcement learning is an enduring challenge.
