Attribute Controlled Dialogue Prompting
- URL: http://arxiv.org/abs/2307.05228v1
- Date: Tue, 11 Jul 2023 12:48:55 GMT
- Title: Attribute Controlled Dialogue Prompting
- Authors: Runcheng Liu, Ahmad Rashid, Ivan Kobyzev, Mehdi Rezagholizadeh and
Pascal Poupart
- Abstract summary: We present a novel, instance-specific prompt-tuning algorithm for dialogue generation.
Our method is superior to prompting baselines and comparable to fine-tuning with only 5%-6% of total parameters.
- Score: 31.09791656949115
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Prompt-tuning has become an increasingly popular parameter-efficient method
for adapting large pretrained language models to downstream tasks. However,
both discrete prompting and continuous prompting assume fixed prompts for all
data samples within a task, neglecting the fact that inputs vary greatly in
some tasks such as open-domain dialogue generation. In this paper, we present a
novel, instance-specific prompt-tuning algorithm for dialogue generation.
Specifically, we generate prompts based on instance-level control code, rather
than the conversation history, to explore their impact on controlled dialogue
generation. Experiments on popular open-domain dialogue datasets, evaluated on
both automated metrics and human evaluation, demonstrate that our method is
superior to prompting baselines and comparable to fine-tuning with only 5%-6%
of total parameters.
Related papers
- A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation [37.79563028123686]
In open domain multi turn dialogue generation, it is essential to modeling the contextual semantics of the dialogue history.
Previous research had verified the effectiveness of the hierarchical recurrent encoder-decoder framework on open domain multi turn dialogue generation.
We propose a static and dynamic attention-based approach to model the dialogue history and then generate open domain multi turn dialogue responses.
arXiv Detail & Related papers (2024-10-28T06:05:34Z) - Contextual Data Augmentation for Task-Oriented Dialog Systems [8.085645180329417]
We develop a novel dialog augmentation model that generates a user turn, conditioning on full dialog context.
With a new prompt design for language model, and output re-ranking, the dialogs generated from our model can be directly used to train downstream dialog systems.
arXiv Detail & Related papers (2023-10-16T13:22:34Z) - Controllable Mixed-Initiative Dialogue Generation through Prompting [50.03458333265885]
Mixed-initiative dialogue tasks involve repeated exchanges of information and conversational control.
Agents gain control by generating responses that follow particular dialogue intents or strategies, prescribed by a policy planner.
Standard approach has been fine-tuning pre-trained language models to perform generation conditioned on these intents.
We instead prompt large language models as a drop-in replacement to fine-tuning on conditional generation.
arXiv Detail & Related papers (2023-05-06T23:11:25Z) - Contextual Dynamic Prompting for Response Generation in Task-oriented
Dialog Systems [8.419582942080927]
Response generation is one of the critical components in task-oriented dialog systems.
We propose an approach that performs textit dynamic prompting where the prompts are learnt from dialog contexts.
We show that contextual dynamic prompts improve response generation in terms of textit combined score citemehri-etal 2019-structured by 3 absolute points.
arXiv Detail & Related papers (2023-01-30T20:26:02Z) - DIONYSUS: A Pre-trained Model for Low-Resource Dialogue Summarization [127.714919036388]
DIONYSUS is a pre-trained encoder-decoder model for summarizing dialogues in any new domain.
Our experiments show that DIONYSUS outperforms existing methods on six datasets.
arXiv Detail & Related papers (2022-12-20T06:21:21Z) - Controllable Dialogue Simulation with In-Context Learning [39.04491297557292]
textscDialogic is a dialogue simulation method based on large language model in-context learning.
Our method can rapidly expand a small set of dialogue data with minimum or zero human involvement.
Our simulated dialogues have near-human fluency and annotation accuracy.
arXiv Detail & Related papers (2022-10-09T06:32:58Z) - Manual-Guided Dialogue for Flexible Conversational Agents [84.46598430403886]
How to build and use dialogue data efficiently, and how to deploy models in different domains at scale can be critical issues in building a task-oriented dialogue system.
We propose a novel manual-guided dialogue scheme, where the agent learns the tasks from both dialogue and manuals.
Our proposed scheme reduces the dependence of dialogue models on fine-grained domain ontology, and makes them more flexible to adapt to various domains.
arXiv Detail & Related papers (2022-08-16T08:21:12Z) - GODEL: Large-Scale Pre-Training for Goal-Directed Dialog [119.1397031992088]
We introduce GODEL, a large pre-trained language model for dialog.
We show that GODEL outperforms state-of-the-art pre-trained dialog models in few-shot fine-tuning setups.
A novel feature of our evaluation methodology is the introduction of a notion of utility that assesses the usefulness of responses.
arXiv Detail & Related papers (2022-06-22T18:19:32Z) - Rethinking Dialogue State Tracking with Reasoning [76.0991910623001]
This paper proposes to track dialogue states gradually with reasoning over dialogue turns with the help of the back-end data.
Empirical results demonstrate that our method significantly outperforms the state-of-the-art methods by 38.6% in terms of joint belief accuracy for MultiWOZ 2.1.
arXiv Detail & Related papers (2020-05-27T02:05:33Z) - Learning an Unreferenced Metric for Online Dialogue Evaluation [53.38078951628143]
We propose an unreferenced automated evaluation metric that uses large pre-trained language models to extract latent representations of utterances.
We show that our model achieves higher correlation with human annotations in an online setting, while not requiring true responses for comparison during inference.
arXiv Detail & Related papers (2020-05-01T20:01:39Z)
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.