Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning

Abstract

Text matching is a fundamental technique in both information retrieval and natural language processing. Text matching tasks share the same paradigm that determines the relationship between two given texts. The relationships vary from task to task, e.g.~relevance in document retrieval, semantic alignment in paraphrase identification and answerable judgment in question answering. However, the essential signals for text matching remain in a finite scope, i.e.~exact matching, semantic matching, and inference matching. Ideally, a good text matching model can learn to capture and aggregate these signals for different matching tasks to achieve competitive performance, while recent state-of-the-art text matching models, e.g.~Pre-trained Language Models (PLMs), are hard to generalize. It is because the end-to-end supervised learning on task-specific dataset makes model overemphasize the data sample bias and task-specific signals instead of the essential matching signals. To overcome this problem, we adopt a specialization-generalization training strategy and refer to it as Match-Prompt. In specialization stage, descriptions of different matching tasks are mapped to a few prompt tokens. In generalization stage, matching model explores the essential matching signals by being trained on diverse matching tasks. High diverse matching tasks avoid model fitting the data bias on a specific task, so that model can focus on learning the essential matching signals. Meanwhile, the prompt tokens obtained in the first step help the model distinguish different task-specific matching signals. Experimental results on public datasets show that Match-Prompt can improve multi-task generalization capability of PLMs in text matching and yield better in-domain multi-task, out-of-domain multi-task and new task adaptation performance than multi-task and task-specific models trained by previous fine-tuning paradigm.

Accepted by CIKM 2022

References in corpus (10)

• A Deep Relevance Matching Model for Ad-hoc Retrieval
• DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
• Multitask Prompted Training Enables Zero-Shot Task Generalization
• Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
• PPT: Pre-trained Prompt Tuning for Few-shot Learning
• Zero-shot Text Classification With Generative Language Models
• Using Prior Knowledge to Guide BERT's Attention in Semantic Textual Matching Tasks
• Description Based Text Classification with Reinforcement Learning
• Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching
• A Linguistic Study on Relevance Modeling in Information Retrieval

Cited by in corpus (2)

• Neural Retrievers are Biased Towards LLM-Generated Content
• Leveraging Prompt Learning and Pause Encoding for Alzheimer's Disease Detection