Federated Natural Language Generation for Personalized Dialogue System
- URL: http://arxiv.org/abs/2110.06419v1
- Date: Wed, 13 Oct 2021 00:59:52 GMT
- Title: Federated Natural Language Generation for Personalized Dialogue System
- Authors: Yujie Lu, Chao Huang, Huanli Zhan, Yong Zhuang
- Abstract summary: We propose a novel Federated Natural Language Generation framework, which learns personalized representations from various dataset on distributed devices.
FedNLG first pre-trains parameters of standard neural conversational model over a large dialogue corpus, and then fine-tune the model parameters and persona embeddings on specific datasets.
We demonstrate the effectiveness of our model by pre-training model over Cornell Movie-Dialogs Corpus and fine-tuning the model over two TV series dataset.
- Score: 5.649931633964224
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Neural conversational models have long suffered from the problem of
inconsistency and lacking coherent personality. To address the issue,
persona-based models capturing individual characteristics have been proposed,
but they still face the dilemma of model adaption and data privacy. To break
this dilemma, we propose a novel Federated Natural Language Generation (FedNLG)
framework, which learns personalized representations from various dataset on
distributed devices, and thus implements the personalized dialogue system
efficiently and safely. FedNLG first pre-trains parameters of standard neural
conversational model over a large dialogue corpus, and then fine-tune the model
parameters and persona embeddings on specific datasets, in a federated manner.
Thus, the model could simultaneously learn the persona embeddings in local
clients and learn shared model parameters by federated aggregation, which
achieves accuracyprivacy balance. By conducting extensive experiments, we
demonstrate the effectiveness of our model by pre-training model over Cornell
Movie-Dialogs Corpus and fine-tuning the model over two TV series dataset.
Related papers
- Generative Pre-training for Speech with Flow Matching [81.59952572752248]
We pre-trained a generative model, named SpeechFlow, on 60k hours of untranscribed speech with Flow Matching and masked conditions.
Experiment results show the pre-trained generative model can be fine-tuned with task-specific data to match or surpass existing expert models on speech enhancement, separation, and synthesis.
arXiv Detail & Related papers (2023-10-25T03:40:50Z) - Federated Learning with Neural Graphical Models [2.6842860806280058]
Federated Learning (FL) addresses the need to create models based on proprietary data.
Recent proposed Neural Graphical Models (NGMs) are Probabilistic Graphical models that utilize the expressive power of neural networks.
We develop a FL framework which maintains a global NGM model that learns the averaged information from the local NGM models.
arXiv Detail & Related papers (2023-09-20T23:24:22Z) - Towards Personalized Federated Learning via Heterogeneous Model
Reassembly [84.44268421053043]
pFedHR is a framework that leverages heterogeneous model reassembly to achieve personalized federated learning.
pFedHR dynamically generates diverse personalized models in an automated manner.
arXiv Detail & Related papers (2023-08-16T19:36:01Z) - Dataless Knowledge Fusion by Merging Weights of Language Models [51.8162883997512]
Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models.
This creates a barrier to fusing knowledge across individual models to yield a better single model.
We propose a dataless knowledge fusion method that merges models in their parameter space.
arXiv Detail & Related papers (2022-12-19T20:46:43Z) - Self-augmented Data Selection for Few-shot Dialogue Generation [18.794770678708637]
We adopt the self-training framework to deal with the few-shot MR-to-Text generation problem.
We propose a novel data selection strategy to select the data that our generation model is most uncertain about.
arXiv Detail & Related papers (2022-05-19T16:25:50Z) - A Model-Agnostic Data Manipulation Method for Persona-based Dialogue
Generation [107.82729587882397]
It is expensive to scale up current persona-based dialogue datasets.
Each data sample in this task is more complex to learn with than conventional dialogue data.
We propose a data manipulation method, which is model-agnostic to be packed with any persona-based dialogue generation model.
arXiv Detail & Related papers (2022-04-21T03:49:54Z) - Dependency-based Mixture Language Models [53.152011258252315]
We introduce the Dependency-based Mixture Language Models.
In detail, we first train neural language models with a novel dependency modeling objective.
We then formulate the next-token probability by mixing the previous dependency modeling probability distributions with self-attention.
arXiv Detail & Related papers (2022-03-19T06:28:30Z) - Unsupervised Paraphrasing with Pretrained Language Models [85.03373221588707]
We propose a training pipeline that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting.
Our recipe consists of task-adaptation, self-supervision, and a novel decoding algorithm named Dynamic Blocking.
We show with automatic and human evaluations that our approach achieves state-of-the-art performance on both the Quora Question Pair and the ParaNMT datasets.
arXiv Detail & Related papers (2020-10-24T11:55:28Z) - Stochastic Natural Language Generation Using Dependency Information [0.7995360025953929]
This article presents a corpus-based model for generating natural language text.
Our model encodes dependency relations from training data through a feature set, then produces a new dependency tree for a given meaning representation.
We show that our model produces high-quality utterances in aspects of informativeness and naturalness as well as quality.
arXiv Detail & Related papers (2020-01-12T09:40:11Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.