Prompt Learning for Domain Adaptation in Task-Oriented Dialogue

• URL: http://arxiv.org/abs/2211.05596v1
• Date: Thu, 10 Nov 2022 14:16:00 GMT
• Title: Prompt Learning for Domain Adaptation in Task-Oriented Dialogue
• Authors: Makesh Narsimhan Sreedhar, Christopher Parisien
• Abstract summary: We show that canonical forms offer a promising alternative to traditional methods for intent classification. We show that canonical forms generalize very well to new, unseen domains in a zero- or few-shot setting.
• Score: 0.20305676256390934
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conversation designers continue to face significant obstacles when creating production quality task-oriented dialogue systems. The complexity and cost involved in schema development and data collection is often a major barrier for such designers, limiting their ability to create natural, user-friendly experiences. We frame the classification of user intent as the generation of a canonical form, a lightweight semantic representation using natural language. We show that canonical forms offer a promising alternative to traditional methods for intent classification. By tuning soft prompts for a frozen large language model, we show that canonical forms generalize very well to new, unseen domains in a zero- or few-shot setting. The method is also sample-efficient, reducing the complexity and effort of developing new task-oriented dialogue domains.

Related papers

• Generative Context Distillation [48.91617280112579]
  Generative Context Distillation (GCD) is a lightweight prompt internalization method that employs a joint training approach. We demonstrate that our approach effectively internalizes complex prompts across various agent-based application scenarios.
  arXiv  Detail & Related papers  (2024-11-24T17:32:20Z)
• A Stack-Propagation Framework for Low-Resource Personalized Dialogue Generation [29.348053519918928]
  We propose a novel stack-propagation framework for learning a dialogue generation and understanding pipeline. The proposed framework can benefit from the stacked encoder and decoders to learn from much smaller personalized dialogue data.
  arXiv  Detail & Related papers  (2024-10-26T13:09:21Z)
• Training-Free Consistent Text-to-Image Generation [80.4814768762066]
  Text-to-image models can portray the same subject across diverse prompts. Existing approaches fine-tune the model to teach it new words that describe specific user-provided subjects. We present ConsiStory, a training-free approach that enables consistent subject generation by sharing the internal activations of the pretrained model.
  arXiv  Detail & Related papers  (2024-02-05T18:42:34Z)
• IntentDial: An Intent Graph based Multi-Turn Dialogue System with Reasoning Path Visualization [24.888848712778664]
  We present a novel graph-based multi-turn dialogue system called. It identifies a user's intent by identifying intent elements and a standard query from a graph using reinforcement learning.
  arXiv  Detail & Related papers  (2023-10-18T09:21:37Z)
• Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking [57.92608483099916]
  Large pre-trained language models (PLMs) have shown impressive unaided performance across many NLP tasks. For more complex tasks such as dialogue state tracking (DST), designing prompts that reliably convey the desired intent is nontrivial. We introduce a saliency model to limit dialogue text length, allowing us to include more exemplars per query.
  arXiv  Detail & Related papers  (2023-02-12T15:05:10Z)
• The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding [65.34601470417967]
  We describe a hybrid architecture for dialogue response generation that combines the strengths of neural language modeling and rule-based generation. Our experiments show that this system outperforms both rule-based and learned approaches in human evaluations of fluency, relevance, and truthfulness.
  arXiv  Detail & Related papers  (2022-09-16T09:00:49Z)
• Response Generation with Context-Aware Prompt Learning [19.340498579331555]
  We present a novel approach for pre-trained dialogue modeling that casts the dialogue generation problem as a prompt-learning task. Instead of fine-tuning on limited dialogue data, our approach, DialogPrompt, learns continuous prompt embeddings optimized for dialogue contexts. Our approach significantly outperforms the fine-tuning baseline and the generic prompt-learning methods.
  arXiv  Detail & Related papers  (2021-11-04T05:40:13Z)
• Learning Adaptive Language Interfaces through Decomposition [89.21937539950966]
  We introduce a neural semantic parsing system that learns new high-level abstractions through decomposition. Users interactively teach the system by breaking down high-level utterances describing novel behavior into low-level steps.
  arXiv  Detail & Related papers  (2020-10-11T08:27:07Z)
• Few-shot Natural Language Generation for Task-Oriented Dialog [113.07438787659859]
  We present FewShotWoz, the first NLG benchmark to simulate the few-shot learning setting in task-oriented dialog systems. We develop the SC-GPT model, which is pre-trained on a large set of annotated NLG corpus to acquire the controllable generation ability. Experiments on FewShotWoz and the large Multi-Domain-WOZ datasets show that the proposed SC-GPT significantly outperforms existing methods.
  arXiv  Detail & Related papers  (2020-02-27T18:48:33Z)

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.