AdaTag: Multi-Attribute Value Extraction from Product Profiles with
Adaptive Decoding
- URL: http://arxiv.org/abs/2106.02318v1
- Date: Fri, 4 Jun 2021 07:54:11 GMT
- Title: AdaTag: Multi-Attribute Value Extraction from Product Profiles with
Adaptive Decoding
- Authors: Jun Yan, Nasser Zalmout, Yan Liang, Christan Grant, Xiang Ren, Xin
Luna Dong
- Abstract summary: We present AdaTag, which uses adaptive decoding to handle attribute extraction.
Our experiments on a real-world e-Commerce dataset show marked improvements over previous methods.
- Score: 55.89773725577615
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Automatic extraction of product attribute values is an important enabling
technology in e-Commerce platforms. This task is usually modeled using sequence
labeling architectures, with several extensions to handle multi-attribute
extraction. One line of previous work constructs attribute-specific models,
through separate decoders or entirely separate models. However, this approach
constrains knowledge sharing across different attributes. Other contributions
use a single multi-attribute model, with different techniques to embed
attribute information. But sharing the entire network parameters across all
attributes can limit the model's capacity to capture attribute-specific
characteristics. In this paper we present AdaTag, which uses adaptive decoding
to handle extraction. We parameterize the decoder with pretrained attribute
embeddings, through a hypernetwork and a Mixture-of-Experts (MoE) module. This
allows for separate, but semantically correlated, decoders to be generated on
the fly for different attributes. This approach facilitates knowledge sharing,
while maintaining the specificity of each attribute. Our experiments on a
real-world e-Commerce dataset show marked improvements over previous methods.
Related papers
- MAC: A Benchmark for Multiple Attributes Compositional Zero-Shot Learning [33.12021227971062]
Compositional Zero-Shot Learning (CZSL) aims to learn semantic primitives (attributes and objects) from seen neglecting and recognize unseen attribute-object compositions.
We introduce the Multi-Attribute Composition dataset, encompassing 18,217 images and 11,067 compositions with comprehensive, representative, and diverse attribute annotations.
Our dataset supports deeper semantic understanding and higher-order attribute associations, providing a more realistic and challenging benchmark for the CZSL task.
arXiv Detail & Related papers (2024-06-18T16:24:48Z) - EAVE: Efficient Product Attribute Value Extraction via Lightweight Sparse-layer Interaction [94.22610101608332]
We propose an Efficient product Attribute Value Extraction (EAVE) approach via lightweight sparse-layer interaction.
We employ a heavy encoder to separately encode the product context and attribute. The resulting non-interacting heavy representations of the context can be cached and reused for all attributes.
Our method achieves significant efficiency gains with neutral or marginal loss in performance when the context is long and number of attributes is large.
arXiv Detail & Related papers (2024-06-10T23:06:38Z) - EIVEN: Efficient Implicit Attribute Value Extraction using Multimodal LLM [52.016009472409166]
EIVEN is a data- and parameter-efficient generative framework for implicit attribute value extraction.
We introduce a novel Learning-by-Comparison technique to reduce model confusion.
Our experiments reveal that EIVEN significantly outperforms existing methods in extracting implicit attribute values.
arXiv Detail & Related papers (2024-04-13T03:15:56Z) - Large Scale Generative Multimodal Attribute Extraction for E-commerce
Attributes [23.105116746332506]
E-commerce websites (e.g. Amazon) have a plethora of structured and unstructured information (text and images) present on the product pages.
Sellers often either don't label or mislabel values of the attributes (e.g. color, size etc.) for their products.
We present a scalable solution for this problem using textbfMXT, consisting of three key components.
arXiv Detail & Related papers (2023-06-01T06:21:45Z) - Label2Label: A Language Modeling Framework for Multi-Attribute Learning [93.68058298766739]
Label2Label is the first attempt for multi-attribute prediction from the perspective of language modeling.
Inspired by the success of pre-training language models in NLP, Label2Label introduces an image-conditioned masked language model.
Our intuition is that the instance-wise attribute relations are well grasped if the neural net can infer the missing attributes based on the context and the remaining attribute hints.
arXiv Detail & Related papers (2022-07-18T15:12:33Z) - OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak
Supervision [93.26737878221073]
We study the attribute mining problem in an open-world setting to extract novel attributes and their values.
We propose a principled framework that first generates attribute value candidates and then groups them into clusters of attributes.
Our model significantly outperforms strong baselines and can generalize to unseen attributes and product types.
arXiv Detail & Related papers (2022-04-29T04:16:04Z) - Multimodal Joint Attribute Prediction and Value Extraction for
E-commerce Product [40.46223408546036]
Product attribute values are essential in many e-commerce scenarios, such as customer service robots, product recommendations, and product retrieval.
While in the real world, the attribute values of a product are usually incomplete and vary over time, which greatly hinders the practical applications.
We propose a multimodal method to jointly predict product attributes and extract values from textual product descriptions with the help of the product images.
arXiv Detail & Related papers (2020-09-15T15:10:51Z) - Automatic Validation of Textual Attribute Values in E-commerce Catalog
by Learning with Limited Labeled Data [61.789797281676606]
We propose a novel meta-learning latent variable approach, called MetaBridge.
It can learn transferable knowledge from a subset of categories with limited labeled data.
It can capture the uncertainty of never-seen categories with unlabeled data.
arXiv Detail & Related papers (2020-06-15T21:31:05Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.