"In Dialogues We Learn": Towards Personalized Dialogue Without
Pre-defined Profiles through In-Dialogue Learning
- URL: http://arxiv.org/abs/2403.03102v3
- Date: Tue, 12 Mar 2024 05:33:16 GMT
- Title: "In Dialogues We Learn": Towards Personalized Dialogue Without
Pre-defined Profiles through In-Dialogue Learning
- Authors: Chuanqi Cheng, Quan Tu, Wei Wu, Shuo Shang, Cunli Mao, Zhengtao Yu,
Rui Yan
- Abstract summary: In-Dialogue Learning (IDL) is a fine-tuning framework that enhances the ability of pre-trained large language models to leverage dialogue history to characterize persona.
Our experiments on three datasets demonstrate that IDL brings substantial improvements, with BLEU and ROUGE scores increasing by up to 200% and 247%, respectively.
- Score: 39.17821560188733
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Personalized dialogue systems have gained significant attention in recent
years for their ability to generate responses in alignment with different
personas. However, most existing approaches rely on pre-defined personal
profiles, which are not only time-consuming and labor-intensive to create but
also lack flexibility. We propose In-Dialogue Learning (IDL), a fine-tuning
framework that enhances the ability of pre-trained large language models to
leverage dialogue history to characterize persona for completing personalized
dialogue generation tasks without pre-defined profiles. Our experiments on
three datasets demonstrate that IDL brings substantial improvements, with BLEU
and ROUGE scores increasing by up to 200% and 247%, respectively. Additionally,
the results of human evaluations further validate the efficacy of our proposed
method.
Related papers
- Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluations [25.115319934091282]
This paper seeks to survey the recent landscape of personalized dialogue generation.
Covering 22 datasets, we highlight benchmark datasets and newer ones enriched with additional features.
We analyze 17 seminal works from top conferences between 2021-2023 and identify five distinct types of problems.
arXiv Detail & Related papers (2024-05-28T09:04:13Z) - SPECTRUM: Speaker-Enhanced Pre-Training for Long Dialogue Summarization [48.284512017469524]
Multi-turn dialogues are characterized by their extended length and the presence of turn-taking conversations.
Traditional language models often overlook the distinct features of these dialogues by treating them as regular text.
We propose a speaker-enhanced pre-training method for long dialogue summarization.
arXiv Detail & Related papers (2024-01-31T04:50:00Z) - Enhancing Large Language Model Induced Task-Oriented Dialogue Systems
Through Look-Forward Motivated Goals [76.69419538047813]
ProToD approach anticipates the future dialogue actions and incorporates the goal-oriented reward signal to enhance ToD systems.
We present a novel evaluation method that assesses ToD systems based on goal-driven dialogue simulations.
Empirical experiments conducted on the MultiWoZ 2.1 dataset demonstrate that our model can achieve superior performance using only 10% of the data.
arXiv Detail & Related papers (2023-09-16T10:56:00Z) - Towards Robust Personalized Dialogue Generation via Order-Insensitive
Representation Regularization [20.722098595079945]
We propose a model-agnostic framework, ORder Insensitive Generation (ORIG), to mitigate the order sensitivity problem.
Experiments on the Persona-Chat dataset justify the effectiveness and superiority of our method.
arXiv Detail & Related papers (2023-05-22T07:24:29Z) - DialogZoo: Large-Scale Dialog-Oriented Task Learning [52.18193690394549]
We aim to build a unified foundation model which can solve massive diverse dialogue tasks.
To achieve this goal, we first collect a large-scale well-labeled dialogue dataset from 73 publicly available datasets.
arXiv Detail & Related papers (2022-05-25T11:17:16Z) - Less is More: Learning to Refine Dialogue History for Personalized
Dialogue Generation [57.73547958927826]
We propose to refine the user dialogue history on a large scale, based on which we can handle more dialogue history and obtain more accurate persona information.
Specifically, we design an MSP model which consists of three personal information refiners and a personalized response generator.
arXiv Detail & Related papers (2022-04-18T02:02:56Z) - Dual Task Framework for Debiasing Persona-grounded Dialogue Dataset [17.403065663306567]
We introduce a data-centric approach for the task of improving persona-conditioned dialogue agents.
Specifically, we augment relevant personas to improve dialogue dataset/agent, by leveraging the primal-dual structure of the two tasks.
Experiments on Persona-Chat show that our approach outperforms pre-trained LMs by an 11.7 point gain in terms of accuracy.
arXiv Detail & Related papers (2022-02-11T04:08:46Z) - Learning to Predict Persona Information forDialogue Personalization
without Explicit Persona Description [10.17868476063421]
We propose a novel approach that learns to predict persona information based on the dialogue history to personalize the dialogue agent.
Experimental results on the PersonaChat dataset show that the proposed method can improve the consistency of generated responses.
A trained persona prediction model can be successfully transferred to other datasets and help generate more relevant responses.
arXiv Detail & Related papers (2021-11-30T03:19:24Z) - Structural Pre-training for Dialogue Comprehension [51.215629336320305]
We present SPIDER, Structural Pre-traIned DialoguE Reader, to capture dialogue exclusive features.
To simulate the dialogue-like features, we propose two training objectives in addition to the original LM objectives.
Experimental results on widely used dialogue benchmarks verify the effectiveness of the newly introduced self-supervised tasks.
arXiv Detail & Related papers (2021-05-23T15:16:54Z)
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.