Lune

ACL Findings2023

MixPAVE: Mix-Prompt Tuning for Few-shot Product Attribute Value Extraction

Li Yang, Qifan Wang, Jingang Wang, Xiaojun Quan, Fuli Feng, Yu Chen, Madian Khabsa, Sinong Wang, Zenglin Xu, Dongfang Liu

Abstract

The task of product attribute value extraction is to identify values of an attribute from product information. Product attributes are important features, which help improve online shopping experience of customers, such as product search, recommendation and comparison. Most existing works only focus on extracting values for a set of known attributes with sufficient training data. However, with the emerging nature of e-commerce, new products with their unique set of new attributes are constantly generated from different retailers and merchants. Collecting a large number of annotations for every new attribute is costly and time consuming. Therefore, it is an important research problem for product attribute value extraction with limited data. In this work, we propose a novel prompt tuning approach with Mixed Prompts for fewshot Attribute Value Extraction, namely Mix-PAVE. Specifically, MixPAVE introduces only a small amount (< 1%) of trainable parameters, i.e., a mixture of two learnable prompts, while keeping the existing extraction model frozen. In this way, MixPAVE not only benefits from parameter-efficient training, but also avoids model overfitting on limited training examples. Experimental results on two product benchmarks demonstrate the superior performance of the proposed approach over several state-of-the-art baselines. A comprehensive set of ablation studies validate the effectiveness of the prompt design, as well as the efficiency of our approach.

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.

6 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • LoRA: Low-Rank Adaptation of Large Language Models cites The Power of Scale for Parameter-Efficient Prompt Tuning
  • LoRA: Low-Rank Adaptation of Large Language Models cites Language Models are Few-Shot Learners
  • TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification cites LoRA: Low-Rank Adaptation of Large Language Models
  • TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification cites Learning to Extract Attribute Value from Product via Question Answering: A Multi-task Approach
  • E2VPT: An Effective and Efficient Approach for Visual Prompt Tuning cites The Power of Scale for Parameter-Efficient Prompt Tuning
  • E2VPT: An Effective and Efficient Approach for Visual Prompt Tuning cites Language Models are Few-Shot Learners
  • E2VPT: An Effective and Efficient Approach for Visual Prompt Tuning cites TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning
  • M²PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning cites LoRA: Low-Rank Adaptation of Large Language Models
  • M²PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning cites The Power of Scale for Parameter-Efficient Prompt Tuning
  • M²PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning cites E2VPT: An Effective and Efficient Approach for Visual Prompt Tuning
  • M²PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning cites Language Models are Few-Shot Learners
  • M²PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning cites Facing the Elephant in the Room: Visual Prompt Tuning or Full finetuning?
  • M²PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning cites APrompt: Attention Prompt Tuning for Efficient Adaptation of Pre-trained Language Models
  • Facing the Elephant in the Room: Visual Prompt Tuning or Full finetuning? cites The Power of Scale for Parameter-Efficient Prompt Tuning
  • Facing the Elephant in the Room: Visual Prompt Tuning or Full finetuning? cites E2VPT: An Effective and Efficient Approach for Visual Prompt Tuning
  • Facing the Elephant in the Room: Visual Prompt Tuning or Full finetuning? cites Language Models are Few-Shot Learners
  • Facing the Elephant in the Room: Visual Prompt Tuning or Full finetuning? cites TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning
  • Facing the Elephant in the Room: Visual Prompt Tuning or Full finetuning? cites APrompt: Attention Prompt Tuning for Efficient Adaptation of Pre-trained Language Models
  • APrompt: Attention Prompt Tuning for Efficient Adaptation of Pre-trained Language Models cites LoRA: Low-Rank Adaptation of Large Language Models
  • APrompt: Attention Prompt Tuning for Efficient Adaptation of Pre-trained Language Models cites The Power of Scale for Parameter-Efficient Prompt Tuning
  • APrompt: Attention Prompt Tuning for Efficient Adaptation of Pre-trained Language Models cites E2VPT: An Effective and Efficient Approach for Visual Prompt Tuning
  • APrompt: Attention Prompt Tuning for Efficient Adaptation of Pre-trained Language Models cites Language Models are Few-Shot Learners
  • APrompt: Attention Prompt Tuning for Efficient Adaptation of Pre-trained Language Models cites TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers6

  1. E2VPT: An Effective and Efficient Approach for Visual Prompt TuningCheng Han, Qifan Wang, Yiming Cui, Zhiwen Cao et al.ICCV 2023 · 108 citations
  2. Facing the Elephant in the Room: Visual Prompt Tuning or Full finetuning?Cheng Han, Qifan Wang, Yiming Cui, Wenguan Wang et al.ICLR 2024 · 43 citations
  3. M²PT: Multimodal Prompt Tuning for Zero-shot Instruction LearningTaowen Wang, Yiyang Liu, James Liang, Junhan Zhao et al.EMNLP 2024 · 31 citations
  4. APrompt: Attention Prompt Tuning for Efficient Adaptation of Pre-trained Language ModelsQifan Wang, Yuning Mao, Jingang Wang, Hanchao Yu et al.EMNLP 2023 · 25 citations
  5. TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value IdentificationYindu Su, Huike Zou, Lin Sun, Ting Zhang et al.ACL 2025 · 4 citations

Builds on17

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  3. TinyTL: Reduce Memory, Not Parameters for Efficient On-Device LearningHan Cai, Chuang Gan, Ligeng Zhu, Song HanNeurIPS 2020 · 375 citations
  4. The Power of Scale for Parameter-Efficient Prompt TuningBrian Lester, Rami Al-Rfou, Noah ConstantEMNLP 2021 · 94 citations
  5. Learning to Extract Attribute Value from Product via Question Answering: A Multi-task ApproachQifan Wang, Li Yang, Bhargav Kanagal, Sumit Sanghai et al.KDD 2020 · 75 citations

Related papers

  1. Multimodal Prompt Learning for Product Title Generation with Extremely Limited LabelsBang Yang, Fenglin Liu, Zheng Li, Qingyu Yin et al.ACL Findings 2023 · 7 citations
  2. OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak SupervisionXinyang Zhang, Chenwei Zhang, Xian Li, Xin Luna Dong et al.WWW 2022 · 36 citations
  3. Multi-Label Zero-Shot Product Attribute-Value ExtractionJiaying Gong, Hoda EldardiryWWW 2024 · 8 citations
  4. Hypergraph-based Zero-shot Multi-modal Product Attribute Value ExtractionJiazhen Hu, Jiaying Gong, Hongda Shen, Hoda EldardiryWWW 2025 · 4 citations
  5. EAVE: Efficient Product Attribute Value Extraction via Lightweight Sparse-layer InteractionLi Yang, Qifan Wang, Jianfeng Chi, Jiahao Liu et al.EMNLP Findings 2024 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines