CLAIApr 9, 2022

PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization

arXiv:2204.04413v2585 citationsh-index: 14
AI Analysis

This addresses the problem of efficient few-shot learning for summarization, offering a parameter-efficient method that is incremental over existing prompt-based approaches.

The paper tackles few-shot abstractive summarization by introducing a novel soft prompts architecture with prompt pre-training and fine-tuning, achieving competitive results with only 0.1% of parameters tuned, outperforming full-model tuning and Prompt Tuning on CNN/DailyMail and XSum datasets.

Few-shot abstractive summarization has become a challenging task in natural language generation. To support it, we designed a novel soft prompts architecture coupled with a prompt pre-training plus fine-tuning paradigm that is effective and tunes only extremely light parameters. The soft prompts include continuous input embeddings across an encoder and a decoder to fit the structure of the generation models. Importantly, a novel inner-prompt placed in the text is introduced to capture document-level information. The aim is to devote attention to understanding the document that better prompts the model to generate document-related content. The first step in the summarization procedure is to conduct prompt pre-training with self-supervised pseudo-data. This teaches the model basic summarizing capabilities. The model is then fine-tuned with few-shot examples. Experimental results on the CNN/DailyMail and XSum datasets show that our method, with only 0.1% of the parameters, outperforms full-model tuning where all model parameters are tuned. It also surpasses Prompt Tuning by a large margin and delivers competitive results against Prefix-Tuning with 3% of the parameters.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes