Using schema.org Annotations for Training and Maintaining Product Matchers

Peeters, Ralph; Primpeli, Anna; Wichtlhuber, Benedikt; Bizer, Christian

doi:10.1145/3405962.3405964

Cited by 12 publications

(17 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The end clusters are considered to be product offers referring to the same product entity, and are used to create training data for entity linking tasks. The work is further extended in later studies by Bizer et al (2019) and Peeters et al (2020b), and it was shown that this automatically created training dataset has a high quality and can be used to effectively train product entity matchers at high accuracy.…”

Section: Semantic Markup Data As Language Resourcesmentioning

confidence: 97%

“…The same authors also used a product corpus to train a domain-specific word embedding model in Peeters et al (2020b). Specifically, they extracted the brand, name and description properties annotated by schema.org from the same corpus above, to create a text corpus that is used to train fastText embeddings.…”

Section: Semantic Markup Data As Language Resourcesmentioning

confidence: 99%

“…The WDC project released several product linking datasets by parsing and annotating samples of the CommonCrawl corpus. These are used in later studies such as Peeters et al (2020b). We use the 'small' dataset as reported in Peeters et al (2020b) for a number of reasons.…”

Section: Product Linkingmentioning

confidence: 99%

“…These are used in later studies such as Peeters et al (2020b). We use the 'small' dataset as reported in Peeters et al (2020b) for a number of reasons. First, the 'small', 'medium', 'large' The DeepMatcher project released 13 datasets for evaluating entity linking while not all of them are related to the product domain.…”

Section: Product Linkingmentioning

confidence: 99%

See 3 more Smart Citations

An Exploratory Study on Utilising the Web of Linked Data for Product Data Mining

Zhang¹,

Song²

2021

Preprint

View full text Add to dashboard Cite

The Linked Open Data practice has led to a significant growth of structured data on the Web in the last decade. Such structured data describe real-world entities in a machine-readable way, and have created an unprecedented opportunity for research in the field of Natural Language Processing. However, there is a lack of studies on how such data can be used, for what kind of tasks, and to what extent they can be useful for these tasks. This work focuses on the e-commerce domain to explore methods of utilising such structured data to create language resources that may be used for product classification and linking. We process billions of structured data points in the form of RDF n-quads, to create multi-million words of product-related corpora that are later used in three different ways for creating of language resources: training word embedding models, continued pretraining of BERT-like language models, and training Machine Translation models that are used as a proxy to generate product-related keywords. Our evaluation on an extensive set of benchmarks shows word embeddings to be the most reliable and consistent method to improve the accuracy on both tasks (with up to 6.9 percentage points in macro-average F1 on some datasets). The other two methods however, are not as useful. Our analysis shows that this could be due to a number of reasons, including the biased domain representation in the structured data and lack of vocabulary coverage. We share our datasets and discuss how our lessons learned could be taken forward to inform future research in this direction.Keywords linked data • web of data • schema.org • natural language processing • nlp • data mining • product mining

show abstract

Section: Semantic Markup Data As Language Resourcesmentioning

confidence: 97%

Section: Semantic Markup Data As Language Resourcesmentioning

confidence: 99%

Section: Product Linkingmentioning

confidence: 99%

Section: Product Linkingmentioning

confidence: 99%

See 2 more Smart Citations

An Exploratory Study on Utilising the Web of Linked Data for Product Data Mining

Zhang¹,

Song²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Deepmatcher: For our experiments with Deepmatcher [23], we choose the RNN summarization method which has proven to perform best for the WDC LSPC datasets [26]. We fix the batch size 4 as input for Deepmatcher.…”

Section: Models and Baselinesmentioning

confidence: 99%

Dual-objective fine-tuning of BERT for entity matching

Peeters

Bizer

2021

Proc. VLDB Endow.

Self Cite

View full text Add to dashboard Cite

An increasing number of data providers have adopted shared numbering schemes such as GTIN, ISBN, DUNS, or ORCID numbers for identifying entities in the respective domain. This means for data integration that shared identifiers are often available for a subset of the entity descriptions to be integrated while such identifiers are not available for others. The challenge in these settings is to learn a matcher for entity descriptions without identifiers using the entity descriptions containing identifiers as training data. The task can be approached by learning a binary classifier which distinguishes pairs of entity descriptions for the same real-world entity from descriptions of different entities. The task can also be modeled as a multi-class classification problem by learning classifiers for identifying descriptions of individual entities. We present a dual-objective training method for BERT, called JointBERT, which combines binary matching and multi-class classification, forcing the model to predict the entity identifier for each entity description in a training pair in addition to the match/non-match decision. Our evaluation across five entity matching benchmark datasets shows that dual-objective training can increase the matching performance for seen products by 1% to 5% F1 compared to single-objective Transformer-based methods, given that enough training data is available for both objectives. In order to gain a deeper understanding of the strengths and weaknesses of the proposed method, we compare JointBERT to several other BERT-based matching methods as well as baseline systems along a set of specific matching challenges. This evaluation shows that JointBERT, given enough training data for both objectives, outperforms the other methods on tasks involving seen products, while it underperforms for unseen products. Using a combination of LIME explanations and domain-specific word classes, we analyze the matching decisions of the different deep learning models and conclude that BERT-based models are better at focusing on relevant word classes compared to RNN-based models.

show abstract