Attribute Value Extraction

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.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 26–35 of 35 papers

Title	Date	Tasks	Status
Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product Attribute Extraction	Jun 28, 2022	AttributeAttribute Extraction	—Unverified
Data Quality Estimation Framework for Faster Tax Code Classification	May 1, 2022	AttributeAttribute Value Extraction	—Unverified
Extreme Multi-Label Classification with Label Masking for Product Attribute Value Extraction	May 1, 2022	AttributeAttribute Value Extraction	—Unverified
QUEACO: Borrowing Treasures from Weakly-labeled Behavior Data for Query Attribute Value Extraction	Aug 19, 2021	AttributeAttribute Value Extraction	—Unverified
Learning Cross-Task Attribute - Attribute Similarity for Multi-task Attribute-Value Extraction	Aug 1, 2021	AttributeAttribute Value Extraction	—Unverified
Attribute Value Generation from Product Title using Language Models	Aug 1, 2021	AttributeAttribute Value Extraction	—Unverified
AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding	Jun 4, 2021	AttributeAttribute Extraction	—Unverified
Learning to Extract Attribute Value from Product via Question Answering: A Multi-task Approach	Aug 20, 2020	AttributeAttribute Value Extraction	—Unverified
Scaling up Open Tagging from Tens to Thousands: Comprehension Empowered Attribute Value Extraction from Product Title	Jul 1, 2019	AttributeAttribute Value Extraction	CodeCode Available
OpenTag: Open Attribute Value Extraction from Product Profiles [Deep Learning, Active Learning, Named Entity Recognition]	Jun 1, 2018	Active LearningAttribute	CodeCode Available

Show:10 25 50

← PrevPage 2 of 2Next →

All datasets WDC-PAVE MAVE AE-110k OA-Mine - annotations

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	GPT-4_10_example_values_&_10_demonstrations	F1-Score	90.54	—	Unverified
2	GPT-3.5_10_example_values_&_10_demonstrations	F1-Score	88.02	—	Unverified
3	AVEQA	F1-Score	80.83	—	Unverified
4	MAVEQA	F1-Score	65.1	—	Unverified
5	SU-OpenTag	F1-Score	60.44	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MAVEQA	F1-score	98.32	—	Unverified
2	AVEQA	F1-score	98.14	—	Unverified
3	AD-Opentag	F1-score	79.73	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GPT-4-json-val-10-dem	F1-score	87.5	—	Unverified
2	ft-GPT-3.5-json-val	F1-score	86	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ft-GPT-3.5-json-val	F1-score	84.5	—	Unverified
2	GPT-4-json-val-10-dem	F1-score	82.2	—	Unverified