Training Conversational Agents with Generative Conversational Networks
Not on the map. Why?
Abstract (arXiv)
Rich, open-domain textual data available on the web resulted in great advancements for language processing. However, while that data may be suitable for language processing tasks, they are mostly non-conversational, lacking many phenomena that appear in human interactions and this is one of the reasons why we still have many unsolved challenges in conversational AI. In this work, we attempt to address this by using Generative Conversational Networks to automatically generate data and train social conversational agents. We evaluate our approach on TopicalChat with automatic metrics and human evaluators, showing that with 10% of seed data it performs close to the baseline that uses 100% of the data.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 16 references that are in the map. First posted on arXiv 15 Oct 2021.
Builds on
11 of 16 references.
References · 11
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
- 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
- 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
- 2021Generating Datasets with Pretrained Language Modelscited by 193
- 2020Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Trackingcited by 65
- 2021Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systemscited by 23
- 2021GenSF: Simultaneous Adaptation of Generative Pre-trained Models and Slot Fillingcited by 11
- 2021Generative Conversational Networkscited by 11
- 2021ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classificationcited by 8
Built on by
Not cited yet.