Lune

EMNLP Findings2022

Instance-Guided Prompt Learning for Few-Shot Text Matching

Jia Du, Xuanyu Zhang, Siyi Wang, Kai Wang, Yanquan Zhou, Lei Li, Qing Yang, Dongliang Xu

Abstract

Few-shot text matching is a more practical technique in natural language processing (NLP) to determine whether two texts are semantically identical. Recent studies based on prompt learning have shown remarkable results. These methods primarily employ uniform prompt patterns for all instances. But they fail to take into account the connection between prompts and instances. This paper argues that dynamically strengthening the correlation between particular instances and the prompts is necessary because fixed prompts cannot adequately fit all diverse instances in inference. Thus, we propose IGATE: Instance-Guided prompt leArning for few-shoT tExt matching, a novel pluggable prompt learning method. The gate mechanism between embedding and encoder of the PLM makes use of the semantics of instances to regulate the effects of the gate on the prompt tokens. The experimental findings show that IGATE achieves SOTA performance on MRPC and QQP, outperforming strong baselines. Our codes are available at https://github.com/Du-Jia/IGATE.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Dual Context-Guided Continuous Prompt Tuning for Few-Shot Learning cites Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners
  • Dual Context-Guided Continuous Prompt Tuning for Few-Shot Learning cites AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts
  • Dual Context-Guided Continuous Prompt Tuning for Few-Shot Learning cites Language Models are Few-Shot Learners
  • Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners cites AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts
  • Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners cites Language Models are Few-Shot Learners
  • Dynamic Prefix-Tuning for Generative Template-based Event Extraction cites AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts
  • AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts cites Language Models are Few-Shot Learners
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on7

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated PromptsTaylor Shin, Yasaman Razeghi, Robert L. Logan IV, Eric Wallace et al.EMNLP 2020 · 1,162 citations
  3. Differentiable Prompt Makes Pre-trained Language Models Better Few-shot LearnersNingyu Zhang, Luoqiu Li, Xiang Chen, Shumin Deng et al.ICLR 2022 · 205 citations
  4. Dynamic Prefix-Tuning for Generative Template-based Event ExtractionXiao Liu, Heyan Huang, Ge Shi, Bo WangACL 2022 · 120 citations
  5. Dual Context-Guided Continuous Prompt Tuning for Few-Shot LearningJie Zhou, Le Tian, Houjin Yu, Xiao Zhou et al.ACL Findings 2022 · 7 citations

Related papers

  1. Zero-shot Approach to Overcome Perturbation Sensitivity of PromptsMohna Chakraborty, Adithya Kulkarni, Qi LiACL 2023 · 6 citations
  2. MetricPrompt: Prompting Model as a Relevance Metric for Few-shot Text ClassificationHongyuan Dong, Weinan Zhang, Wanxiang CheKDD 2023 · 2 citations
  3. Parameter-free Automatically Prompting: A Latent Pseudo Label Mapping Model for Prompt-based LearningJirui Qi, Richong Zhang, Junfan Chen, Jaein Kim et al.EMNLP Findings 2022
  4. GPS: Genetic Prompt Search for Efficient Few-Shot LearningHanwei Xu, Yujun Chen, Yulun Du, Nan Shao et al.EMNLP 2022 · 25 citations
  5. PPT: Pre-trained Prompt Tuning for Few-shot LearningYuxian Gu, Xu Han, Zhiyuan Liu, Minlie HuangACL 2022
Dusk over the sea between two cliffs drawn in fine vertical lines