Details
| Original language | English |
|---|---|
| Title of host publication | WWW 2022 - Companion Proceedings of the Web Conference 2022 |
| Pages | 121-125 |
| Number of pages | 5 |
| ISBN (electronic) | 9781450391306 |
| Publication status | Published - 25 Apr 2022 |
| Event | 31st ACM Web Conference, WWW 2022 - Virtual, Online, France Duration: 25 Apr 2022 → 29 Apr 2022 |
Abstract
A search on the major eCommerce platforms returns up to thousands of relevant products making it impossible for an average customer to audit all the results. Browsing the list of relevant items can be simplified using search filters for specific requirements (e.g., shoes of the wrong size). The complete list of available filters is often overwhelming and hard to visualize. Thus, successful user interfaces desire to display only the ones relevant to customer queries. In this work, we frame the filter selection task as an extreme multi-label classification (XMLC) problem based on historical interaction with eCommerce sites. We learn from customers' clicks and purchases which subset of filters is most relevant to their queries treating the relevant/not-relevant signal as binary labels. A common problem in classification settings with a large number of classes is that some classes are underrepresented. These rare categories are difficult to predict. Building on previous work we show that classification performance for rare classes can be improved by accounting for the language structure of the class labels. Furthermore, our results demonstrate that including language structure in category names enables relatively simple deep learning models to achieve better predictive performance than transformer networks with much higher capacity.
Keywords
- Information Retrieval, Ranking, Search Filters
ASJC Scopus subject areas
- Computer Science(all)
- Computer Networks and Communications
- Computer Science(all)
- Software
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
WWW 2022 - Companion Proceedings of the Web Conference 2022. 2022. p. 121-125.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Search Filter Ranking with Language-Aware Label Embeddings
AU - Golebiowski, Jacek
AU - Merra, Felice Antonio
AU - Abedjan, Ziawasch
AU - Biessmann, Felix
PY - 2022/4/25
Y1 - 2022/4/25
N2 - A search on the major eCommerce platforms returns up to thousands of relevant products making it impossible for an average customer to audit all the results. Browsing the list of relevant items can be simplified using search filters for specific requirements (e.g., shoes of the wrong size). The complete list of available filters is often overwhelming and hard to visualize. Thus, successful user interfaces desire to display only the ones relevant to customer queries. In this work, we frame the filter selection task as an extreme multi-label classification (XMLC) problem based on historical interaction with eCommerce sites. We learn from customers' clicks and purchases which subset of filters is most relevant to their queries treating the relevant/not-relevant signal as binary labels. A common problem in classification settings with a large number of classes is that some classes are underrepresented. These rare categories are difficult to predict. Building on previous work we show that classification performance for rare classes can be improved by accounting for the language structure of the class labels. Furthermore, our results demonstrate that including language structure in category names enables relatively simple deep learning models to achieve better predictive performance than transformer networks with much higher capacity.
AB - A search on the major eCommerce platforms returns up to thousands of relevant products making it impossible for an average customer to audit all the results. Browsing the list of relevant items can be simplified using search filters for specific requirements (e.g., shoes of the wrong size). The complete list of available filters is often overwhelming and hard to visualize. Thus, successful user interfaces desire to display only the ones relevant to customer queries. In this work, we frame the filter selection task as an extreme multi-label classification (XMLC) problem based on historical interaction with eCommerce sites. We learn from customers' clicks and purchases which subset of filters is most relevant to their queries treating the relevant/not-relevant signal as binary labels. A common problem in classification settings with a large number of classes is that some classes are underrepresented. These rare categories are difficult to predict. Building on previous work we show that classification performance for rare classes can be improved by accounting for the language structure of the class labels. Furthermore, our results demonstrate that including language structure in category names enables relatively simple deep learning models to achieve better predictive performance than transformer networks with much higher capacity.
KW - Information Retrieval
KW - Ranking
KW - Search Filters
UR - http://www.scopus.com/inward/record.url?scp=85137457223&partnerID=8YFLogxK
U2 - 10.1145/3487553.3524218
DO - 10.1145/3487553.3524218
M3 - Conference contribution
AN - SCOPUS:85137457223
SP - 121
EP - 125
BT - WWW 2022 - Companion Proceedings of the Web Conference 2022
T2 - 31st ACM Web Conference, WWW 2022
Y2 - 25 April 2022 through 29 April 2022
ER -