Lune

ACL Findings2023

Pay Attention to Implicit Attribute Values: A Multi-modal Generative Framework for AVE Task

Yupeng Zhang, Shensi Wang, Peiguang Li, Guanting Dong, Sirui Wang, Yunsen Xian, Zhoujun Li, Hongzhi Zhang

Abstract

Attribute Value Extraction (AVE) boosts many e-commerce platform services such as targeted recommendation, product retrieval and question answering. Most previous studies adopt an extractive framework such as named entity recognition (NER) to capture subtokens in the product descriptions as the corresponding values of target attributes. However, in the real world scenario, there also exist implicit attribute values that are not mentioned explicitly but embedded in the image information and implied text meaning of products, for which the power of extractive methods is severely constrained. To address the above issues, we exploit a unified multi-modal AVE framework named DEFLATE (a multi-modal unifieD framEwork For impLicit And expliciT AVE) to acquire implicit attribute values in addition to the explicit ones. DEFLATE consists of a QA-based generation model to produce candidate attribute values from the product information of different modalities, and a discriminative model to ensure the credibility of the generated answers. Meanwhile, to provide a testbed that close to the real world, we collect and annotate a multi-modal dataset with parts of implicit attribute values. Extensive experiments conducted on multiple datasets demonstrate that DEFLATE significantly outperforms previous methods on the extraction of implicit attribute values, while achieving comparable performances for the explicit ones.

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.

2 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

  • Multi-Label Zero-Shot Product Attribute-Value Extraction cites Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product
  • Multi-Label Zero-Shot Product Attribute-Value Extraction cites Learning to Extract Attribute Value from Product via Question Answering: A Multi-task Approach
  • Hypergraph-based Zero-shot Multi-modal Product Attribute Value Extraction cites Multi-Label Zero-Shot Product Attribute-Value Extraction
  • Hypergraph-based Zero-shot Multi-modal Product Attribute Value Extraction cites Learning to Extract Attribute Value from Product via Question Answering: A Multi-task Approach
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. Multi-Label Zero-Shot Product Attribute-Value ExtractionJiaying Gong, Hoda EldardiryWWW 2024 · 8 citations
  2. Hypergraph-based Zero-shot Multi-modal Product Attribute Value ExtractionJiazhen Hu, Jiaying Gong, Hongda Shen, Hoda EldardiryWWW 2025 · 4 citations

Builds on5

  1. Zero-Shot Text-to-Image GenerationAditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray et al.ICML 2021 · 6,356 citations
  2. Unifying Vision-and-Language Tasks via Text GenerationJaemin Cho, Jie Lei, Hao Tan, Mohit BansalICML 2021 · 624 citations
  3. 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
  4. Multimodal Joint Attribute Prediction and Value Extraction for E-commerce ProductTiangang Zhu, Yue Wang, Haoran Li, Youzheng Wu et al.EMNLP 2020 · 46 citations
  5. TXtract: Taxonomy-Aware Knowledge Extraction for Thousands of Product CategoriesGiannis Karamanolakis, Jun Ma, Xin Luna DongACL 2020 · 3 citations

Related papers

  1. SMARTAVE: Structured Multimodal Transformer for Product Attribute Value ExtractionQifan Wang, Li Yang, Jingang Wang, Jitin Krishnan et al.EMNLP Findings 2022 · 12 citations
  2. ImplicitAVE: An Open-Source Dataset and Multimodal LLMs Benchmark for Implicit Attribute Value ExtractionHenry Peng Zou, Vinay Samuel, Yue Zhou, Weizhi Zhang et al.ACL Findings 2024 · 10 citations
  3. Knowledge-Selective Pretraining for Attribute Value ExtractionHui Liu, Qingyu Yin, Zhengyang Wang, Chenwei Zhang et al.EMNLP Findings 2023 · 1 citation
  4. CoMave: Contrastive Pre-training with Multi-scale Masking for Attribute Value ExtractionXinnan Guo, Wentao Deng, Yongrui Chen, Yang Li et al.ACL Findings 2023 · 1 citation
  5. 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
Dusk over the sea between two cliffs drawn in fine vertical lines