Attribute Value Extraction
16 papers with code • 4 benchmarks • 6 datasets
Attribute Value Extraction is the task of extracting values for a given set of attributes of interest from free text input. Attribute value extraction is for example applied in the context of e-commerce where product attribute values are extracted from product offers.
The related task Attribute Mining assume that the target attribute set is unknown, while attribute value extraction assumes that the attribute set is given. Multimodal Attribute Extraction aims at extracting attribute values from multi-modal input such as text plus images.
Benchmarks
These leaderboards are used to track progress in Attribute Value Extraction
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
MAVE
AE-110k
OA-Mine - annotations
WDC-PAVE
Caselaw4
MAVE - Attribute: Black Tea Variety
Most implemented papers
OpenTag: Open Attribute Value Extraction from Product Profiles [Deep Learning, Active Learning, Named Entity Recognition]
hackerxiaobai/OpenTag_2019
•
•
We study this problem in the context of product catalogs that often have missing values for many attributes of interest.
Scaling up Open Tagging from Tens to Thousands: Comprehension Empowered Attribute Value Extraction from Product Title
hackerxiaobai/OpenTag_2019
•
•
ACL 2019
Supplementing product information by extracting attribute values from title is a crucial task in e-Commerce domain.
Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product
We annotate a multimodal product attribute value dataset that contains 87, 194 instances, and the experimental results on this dataset demonstrate that explicitly modeling the relationship between attributes and values facilitates our method to establish the correspondence between them, and selectively utilizing visual product information is necessary for the task.
Knowledge-guided Open Attribute Value Extraction with Reinforcement Learning
yeliu0930/Knowledge-guided-Open-Attribute-Value-Extraction-with-Reinforcement-Learning
•
•
EMNLP 2020
Effectively filtering out noisy articles as well as bad answers is the key to improving extraction accuracy.
MAVE: A Product Dataset for Multi-source Attribute Value Extraction
Attribute value extraction refers to the task of identifying values of an attribute of interest from product information.
OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak Supervision
xinyangz/oamine
•
•
Most prior works on this matter mine new values for a set of known attributes but cannot handle new attributes that arose from constantly changing data.
CAVE: Correcting Attribute Values in E-commerce Profiles
To the best of our knowledge, CAVE is the first system that allows users to experiment with a number of powerful QA models and compare their performances on attribute values correction using real-word datasets.
Knowledge-Enhanced Multi-Label Few-Shot Product Attribute-Value Extraction
gjiaying/keaf
•
•
Existing attribute-value extraction (AVE) models require large quantities of labeled data for training.
AE-smnsMLC: Multi-Label Classification with Semantic Matching and Negative Label Sampling for Product Attribute Value Extraction
In this paper, we reformulate this task as a multi-label classification task that can be applied for real-world scenario in which only annotation of attribute values is available to train models (i. e., annotation of positional information of attribute values is not available).
ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction
E-commerce platforms require structured product data in the form of attribute-value pairs to offer features such as faceted product search or attribute-based product comparison.
