Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer in
Prompt Tuning
- URL: http://arxiv.org/abs/2305.12077v2
- Date: Tue, 27 Feb 2024 02:51:16 GMT
- Title: Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer in
Prompt Tuning
- Authors: Kaige Xie, Tong Yu, Haoliang Wang, Junda Wu, Handong Zhao, Ruiyi
Zhang, Kanak Mahadik, Ani Nenkova, Mark Riedl
- Abstract summary: Skeleton-Assisted Prompt Transfer improves prompt transfer from dialogue state tracking to dialogue summarization.
We propose a novel approach with perturbation-based probes requiring neither annotation effort nor domain knowledge.
In-depth analyses demonstrate the effectiveness of our method in facilitating cross-task knowledge transfer in few-shot dialogue summarization.
- Score: 47.336815771549524
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In real-world scenarios, labeled samples for dialogue summarization are
usually limited (i.e., few-shot) due to high annotation costs for high-quality
dialogue summaries. To efficiently learn from few-shot samples, previous works
have utilized massive annotated data from other downstream tasks and then
performed prompt transfer in prompt tuning so as to enable cross-task knowledge
transfer. However, existing general-purpose prompt transfer techniques lack
consideration for dialogue-specific information. In this paper, we focus on
improving the prompt transfer from dialogue state tracking to dialogue
summarization and propose Skeleton-Assisted Prompt Transfer (SAPT), which
leverages skeleton generation as extra supervision that functions as a medium
connecting the distinct source and target task and resulting in the model's
better consumption of dialogue state information. To automatically extract
dialogue skeletons as supervised training data for skeleton generation, we
design a novel approach with perturbation-based probes requiring neither
annotation effort nor domain knowledge. Training the model on such skeletons
can also help preserve model capability during prompt transfer. Our method
significantly outperforms existing baselines. In-depth analyses demonstrate the
effectiveness of our method in facilitating cross-task knowledge transfer in
few-shot dialogue summarization.
Related papers
- Pre-training Multi-party Dialogue Models with Latent Discourse Inference [85.9683181507206]
We pre-train a model that understands the discourse structure of multi-party dialogues, namely, to whom each utterance is replying.
To fully utilize the unlabeled data, we propose to treat the discourse structures as latent variables, then jointly infer them and pre-train the discourse-aware model.
arXiv Detail & Related papers (2023-05-24T14:06:27Z) - Continual Dialogue State Tracking via Example-Guided Question Answering [48.31523413835549]
We propose reformulating dialogue state tracking as a bundle of granular example-guided question answering tasks.
Our approach alleviates service-specific memorization and teaches a model to contextualize the given question and example.
We find that a model with just 60M parameters can achieve a significant boost by learning to learn from in-context examples retrieved by a retriever trained to identify turns with similar dialogue state changes.
arXiv Detail & Related papers (2023-05-23T06:15:43Z) - 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) - 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) - DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context
Tuning [7.5700317050237365]
We propose DiSTRICT, a generalizable in-context tuning approach for Dialogue State Tracking (DST)
DSTRICT retrieves highly relevant training examples for a given dialogue to fine-tune the model without any hand-crafted templates.
Experiments with the MultiWOZ benchmark datasets show that DiSTRICT outperforms existing approaches in various zero-shot and few-shot settings.
arXiv Detail & Related papers (2022-12-06T09:40:15Z) - He Said, She Said: Style Transfer for Shifting the Perspective of
Dialogues [75.58367095888914]
We define a new style transfer task: perspective shift, which reframes a dialogue from informal first person to a formal third person rephrasing of the text.
As a sample application, we demonstrate that applying perspective shifting to a dialogue summarization dataset (SAMSum) substantially improves the zero-shot performance of extractive news summarization models.
arXiv Detail & Related papers (2022-10-27T14:16:07Z) - Leveraging Non-dialogue Summaries for Dialogue Summarization [1.0742675209112622]
We apply transformations to document summarization data pairs to create training data that better befit dialogue summarization.
We conduct extensive experiments across both English and Korean to verify our approach.
arXiv Detail & Related papers (2022-10-17T23:34:31Z) - Utterance Rewriting with Contrastive Learning in Multi-turn Dialogue [22.103162555263143]
We introduce contrastive learning and multi-task learning to jointly model the problem.
Our proposed model achieves state-of-the-art performance on several public datasets.
arXiv Detail & Related papers (2022-03-22T10:13:27Z)
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.