Open-Domain Dialog

32 papers with code • 1 benchmarks • 11 datasets

This task has no description! Would you like to contribute one?

Dior-CVAE: Pre-trained Language Models and Diffusion Priors for Variational Dialog Generation

ukplab/dior-cvae 24 May 2023

These models also suffer from posterior collapse, i. e., the decoder tends to ignore latent variables and directly access information captured in the encoder through the cross-attention mechanism.

1
24 May 2023

Open-Domain Dialog Evaluation using Follow-Ups Likelihood

maximedb/full COLING 2022

Automatic evaluation of open-domain dialogs remains an unsolved problem.

8
12 Sep 2022

Re2G: Retrieve, Rerank, Generate

ibm/kgi-slot-filling NAACL 2022

As demonstrated by GPT-3 and T5, transformers grow in capability as parameter spaces become larger and larger.

124
13 Jul 2022

GODEL: Large-Scale Pre-Training for Goal-Directed Dialog

microsoft/godel 22 Jun 2022

We introduce GODEL (Grounded Open Dialogue Language Model), a large pre-trained language model for dialog.

831
22 Jun 2022

CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI

scutcyr/CPED 29 May 2022

Finally, we provide baseline systems for these tasks and consider the function of speakers' personalities and emotions on conversation.

178
29 May 2022

InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning

prakharguptaz/Instructdial 25 May 2022

We introduce InstructDial, an instruction tuning framework for dialogue, which consists of a repository of 48 diverse dialogue tasks in a unified text-to-text format created from 59 openly available dialogue datasets.

91
25 May 2022

What is wrong with you?: Leveraging User Sentiment for Automatic Dialog Evaluation

alexa/conture Findings (ACL) 2022

Existing model-based metrics for system response evaluation are trained on human annotated data, which is cumbersome to collect.

5
25 Mar 2022

Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarks

para-zhou/cdial-bias 16 Feb 2022

The research of open-domain dialog systems has been greatly prospered by neural models trained on large-scale corpora, however, such corpora often introduce various safety problems (e. g., offensive languages, biases, and toxic behaviors) that significantly hinder the deployment of dialog systems in practice.

20
16 Feb 2022

Investigating Robustness of Dialog Models to Popular Figurative Language Constructs

vgtomahawk/dialog-fig-speech-robust EMNLP 2021

Humans often employ figurative language use in communication, including during interactions with dialog systems.

0
01 Oct 2021

GenSF: Simultaneous Adaptation of Generative Pre-trained Models and Slot Filling

shikib/generative_slot_filling SIGDIAL (ACL) 2021

We instead achieve strong alignment by simultaneously modifying both the pre-trained model and the formulation of the downstream task, which is more efficient and preserves the scalability of transfer learning.

4
13 Jun 2021