Task-Oriented Dialogue Systems
121 papers with code • 4 benchmarks • 19 datasets
Achieving a pre-defined task through a dialog.
Benchmarks
These leaderboards are used to track progress in Task-Oriented Dialogue Systems
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Task-Oriented Dialogue Systems models and implementations
MultiWOZ
SGD
MuTual
CrossWOZ
ABCD
BiToD
Most implemented papers
A Generative Model for Joint Natural Language Understanding and Generation
andy194673/Joint-NLU-NLG
•
•
ACL 2020
This approach allows us to explore both spaces of natural language and formal representations, and facilitates information sharing through the latent space to eventually benefit NLU and NLG.
Diversifying Task-oriented Dialogue Response Generation with Prototype Guided Paraphrasing
phlippe/P2_Net
•
•
Instead of generating a response from scratch, P2-Net generates system responses by paraphrasing template-based responses.
Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems
cszmli/Rethink-RL-Sup
•
•
Findings of the Association for Computational Linguistics 2020
Then, the traditional multi-label classification solution for dialogue policy learning is extended by adding dense layers to improve the dialogue agent performance.
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
In this paper, we propose Minimalist Transfer Learning (MinTL) to simplify the system design process of task-oriented dialogue systems and alleviate the over-dependency on annotated data.
Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems
HLTCHKUST/ke-dialogue
•
•
Findings of the Association for Computational Linguistics 2020
In this paper, we propose a method to embed the KB, of any size, directly into the model parameters.
GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems
shiquanyang/GraphDialog
•
•
EMNLP 2020
End-to-end task-oriented dialogue systems aim to generate system responses directly from plain text inputs.
On Task-Level Dialogue Composition of Generative Transformer Model
ppartha03/Dialogue-Compositionality-of-Generative-Transformer
•
•
EMNLP (insights) 2020
In this work, we begin by studying the effect of training human-human task-oriented dialogues towards improving the ability to compose multiple tasks on Transformer generative models.
Adding Chit-Chat to Enhance Task-Oriented Dialogues
facebookresearch/accentor
•
•
NAACL 2021
Existing dialogue corpora and models are typically designed under two disjoint motives: while task-oriented systems focus on achieving functional goals (e. g., booking hotels), open-domain chatbots aim at making socially engaging conversations.
Conditioned Text Generation with Transfer for Closed-Domain Dialogue Systems
snipsco/automatic-data-generation
•
•
Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation.
LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimization
budzianowski/multiwoz
•
•
COLING 2020
In this paper, we explore three ways of leveraging an auxiliary task to shape the latent variable distribution: via pre-training, to obtain an informed prior, and via multitask learning.
