An Interpretable Ensemble of Graph and Language Models for Improving Search Relevance in E-Commerce
The problem of search relevance in the E-commerce domain is a challenging one since it involves understanding the intent of a user's short nuanced query and matching it with the appropriate products in the catalog. This problem has traditionally been addressed using language models (LMs) and gr...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2024-03 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Choudhary, Nurendra Huang, Edward W Subbian, Karthik Reddy, Chandan K |
description | The problem of search relevance in the E-commerce domain is a challenging one since it involves understanding the intent of a user's short nuanced query and matching it with the appropriate products in the catalog. This problem has traditionally been addressed using language models (LMs) and graph neural networks (GNNs) to capture semantic and inter-product behavior signals, respectively. However, the rapid development of new architectures has created a gap between research and the practical adoption of these techniques. Evaluating the generalizability of these models for deployment requires extensive experimentation on complex, real-world datasets, which can be non-trivial and expensive. Furthermore, such models often operate on latent space representations that are incomprehensible to humans, making it difficult to evaluate and compare the effectiveness of different models. This lack of interpretability hinders the development and adoption of new techniques in the field. To bridge this gap, we propose Plug and Play Graph LAnguage Model (PP-GLAM), an explainable ensemble of plug and play models. Our approach uses a modular framework with uniform data processing pipelines. It employs additive explanation metrics to independently decide whether to include (i) language model candidates, (ii) GNN model candidates, and (iii) inter-product behavioral signals. For the task of search relevance, we show that PP-GLAM outperforms several state-of-the-art baselines as well as a proprietary model on real-world multilingual, multi-regional e-commerce datasets. To promote better model comprehensibility and adoption, we also provide an analysis of the explainability and computational complexity of our model. We also provide the public codebase and provide a deployment strategy for practical implementation. |
doi_str_mv | 10.48550/arxiv.2403.00923 |
format | Article |
fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2403_00923</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2937451775</sourcerecordid><originalsourceid>FETCH-LOGICAL-a953-1fc236c85072ad559d589975c6926e6ec7a26bd29bf6d8e277c10cb0156885163</originalsourceid><addsrcrecordid>eNotkF1LwzAYhYMgOKY_wCsDXncmb_omzeUYcw4mgu6-pOnbraNNa7oN_ffuw6tzLg6Hh4exRykmaYYoXlz8qY8TSIWaCGFB3bARKCWTLAW4Yw_DsBNCgDaAqEbMTwNfhj3FPtLeFQ3xeRioPZeu4ovo-i13oeQrFzYHtyH-3pXUDLzqIl-2feyOddjwL3LRb_knNXR0wROvA58ns65tKXq6Z7eVawZ6-M8xW7_O17O3ZPWxWM6mq8RZVImsPCjtMxQGXIloS8ysNei1BU2avHGgixJsUekyIzDGS-ELIVFnGUqtxuzpensxkPexbl38zc8m8ouJ0-L5ujhxfx9o2Oe77hDDiSkHq0yK0hhUf0_1X9Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2937451775</pqid></control><display><type>article</type><title>An Interpretable Ensemble of Graph and Language Models for Improving Search Relevance in E-Commerce</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Choudhary, Nurendra ; Huang, Edward W ; Subbian, Karthik ; Reddy, Chandan K</creator><creatorcontrib>Choudhary, Nurendra ; Huang, Edward W ; Subbian, Karthik ; Reddy, Chandan K</creatorcontrib><description>The problem of search relevance in the E-commerce domain is a challenging one since it involves understanding the intent of a user's short nuanced query and matching it with the appropriate products in the catalog. This problem has traditionally been addressed using language models (LMs) and graph neural networks (GNNs) to capture semantic and inter-product behavior signals, respectively. However, the rapid development of new architectures has created a gap between research and the practical adoption of these techniques. Evaluating the generalizability of these models for deployment requires extensive experimentation on complex, real-world datasets, which can be non-trivial and expensive. Furthermore, such models often operate on latent space representations that are incomprehensible to humans, making it difficult to evaluate and compare the effectiveness of different models. This lack of interpretability hinders the development and adoption of new techniques in the field. To bridge this gap, we propose Plug and Play Graph LAnguage Model (PP-GLAM), an explainable ensemble of plug and play models. Our approach uses a modular framework with uniform data processing pipelines. It employs additive explanation metrics to independently decide whether to include (i) language model candidates, (ii) GNN model candidates, and (iii) inter-product behavioral signals. For the task of search relevance, we show that PP-GLAM outperforms several state-of-the-art baselines as well as a proprietary model on real-world multilingual, multi-regional e-commerce datasets. To promote better model comprehensibility and adoption, we also provide an analysis of the explainability and computational complexity of our model. We also provide the public codebase and provide a deployment strategy for practical implementation.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2403.00923</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Complexity ; Computer Science - Computation and Language ; Computer Science - Information Retrieval ; Data processing ; Datasets ; Electronic commerce ; Graph neural networks ; Plug & play ; Searching</subject><ispartof>arXiv.org, 2024-03</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by-nc-sa/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://creativecommons.org/licenses/by-nc-sa/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,778,782,883,27908</link.rule.ids><backlink>$$Uhttps://doi.org/10.48550/arXiv.2403.00923$$DView paper in arXiv$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.1145/3589335.3648318$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink></links><search><creatorcontrib>Choudhary, Nurendra</creatorcontrib><creatorcontrib>Huang, Edward W</creatorcontrib><creatorcontrib>Subbian, Karthik</creatorcontrib><creatorcontrib>Reddy, Chandan K</creatorcontrib><title>An Interpretable Ensemble of Graph and Language Models for Improving Search Relevance in E-Commerce</title><title>arXiv.org</title><description>The problem of search relevance in the E-commerce domain is a challenging one since it involves understanding the intent of a user's short nuanced query and matching it with the appropriate products in the catalog. This problem has traditionally been addressed using language models (LMs) and graph neural networks (GNNs) to capture semantic and inter-product behavior signals, respectively. However, the rapid development of new architectures has created a gap between research and the practical adoption of these techniques. Evaluating the generalizability of these models for deployment requires extensive experimentation on complex, real-world datasets, which can be non-trivial and expensive. Furthermore, such models often operate on latent space representations that are incomprehensible to humans, making it difficult to evaluate and compare the effectiveness of different models. This lack of interpretability hinders the development and adoption of new techniques in the field. To bridge this gap, we propose Plug and Play Graph LAnguage Model (PP-GLAM), an explainable ensemble of plug and play models. Our approach uses a modular framework with uniform data processing pipelines. It employs additive explanation metrics to independently decide whether to include (i) language model candidates, (ii) GNN model candidates, and (iii) inter-product behavioral signals. For the task of search relevance, we show that PP-GLAM outperforms several state-of-the-art baselines as well as a proprietary model on real-world multilingual, multi-regional e-commerce datasets. To promote better model comprehensibility and adoption, we also provide an analysis of the explainability and computational complexity of our model. We also provide the public codebase and provide a deployment strategy for practical implementation.</description><subject>Complexity</subject><subject>Computer Science - Computation and Language</subject><subject>Computer Science - Information Retrieval</subject><subject>Data processing</subject><subject>Datasets</subject><subject>Electronic commerce</subject><subject>Graph neural networks</subject><subject>Plug & play</subject><subject>Searching</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotkF1LwzAYhYMgOKY_wCsDXncmb_omzeUYcw4mgu6-pOnbraNNa7oN_ffuw6tzLg6Hh4exRykmaYYoXlz8qY8TSIWaCGFB3bARKCWTLAW4Yw_DsBNCgDaAqEbMTwNfhj3FPtLeFQ3xeRioPZeu4ovo-i13oeQrFzYHtyH-3pXUDLzqIl-2feyOddjwL3LRb_knNXR0wROvA58ns65tKXq6Z7eVawZ6-M8xW7_O17O3ZPWxWM6mq8RZVImsPCjtMxQGXIloS8ysNei1BU2avHGgixJsUekyIzDGS-ELIVFnGUqtxuzpensxkPexbl38zc8m8ouJ0-L5ujhxfx9o2Oe77hDDiSkHq0yK0hhUf0_1X9Q</recordid><startdate>20240301</startdate><enddate>20240301</enddate><creator>Choudhary, Nurendra</creator><creator>Huang, Edward W</creator><creator>Subbian, Karthik</creator><creator>Reddy, Chandan K</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240301</creationdate><title>An Interpretable Ensemble of Graph and Language Models for Improving Search Relevance in E-Commerce</title><author>Choudhary, Nurendra ; Huang, Edward W ; Subbian, Karthik ; Reddy, Chandan K</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a953-1fc236c85072ad559d589975c6926e6ec7a26bd29bf6d8e277c10cb0156885163</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Complexity</topic><topic>Computer Science - Computation and Language</topic><topic>Computer Science - Information Retrieval</topic><topic>Data processing</topic><topic>Datasets</topic><topic>Electronic commerce</topic><topic>Graph neural networks</topic><topic>Plug & play</topic><topic>Searching</topic><toplevel>online_resources</toplevel><creatorcontrib>Choudhary, Nurendra</creatorcontrib><creatorcontrib>Huang, Edward W</creatorcontrib><creatorcontrib>Subbian, Karthik</creatorcontrib><creatorcontrib>Reddy, Chandan K</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Choudhary, Nurendra</au><au>Huang, Edward W</au><au>Subbian, Karthik</au><au>Reddy, Chandan K</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>An Interpretable Ensemble of Graph and Language Models for Improving Search Relevance in E-Commerce</atitle><jtitle>arXiv.org</jtitle><date>2024-03-01</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>The problem of search relevance in the E-commerce domain is a challenging one since it involves understanding the intent of a user's short nuanced query and matching it with the appropriate products in the catalog. This problem has traditionally been addressed using language models (LMs) and graph neural networks (GNNs) to capture semantic and inter-product behavior signals, respectively. However, the rapid development of new architectures has created a gap between research and the practical adoption of these techniques. Evaluating the generalizability of these models for deployment requires extensive experimentation on complex, real-world datasets, which can be non-trivial and expensive. Furthermore, such models often operate on latent space representations that are incomprehensible to humans, making it difficult to evaluate and compare the effectiveness of different models. This lack of interpretability hinders the development and adoption of new techniques in the field. To bridge this gap, we propose Plug and Play Graph LAnguage Model (PP-GLAM), an explainable ensemble of plug and play models. Our approach uses a modular framework with uniform data processing pipelines. It employs additive explanation metrics to independently decide whether to include (i) language model candidates, (ii) GNN model candidates, and (iii) inter-product behavioral signals. For the task of search relevance, we show that PP-GLAM outperforms several state-of-the-art baselines as well as a proprietary model on real-world multilingual, multi-regional e-commerce datasets. To promote better model comprehensibility and adoption, we also provide an analysis of the explainability and computational complexity of our model. We also provide the public codebase and provide a deployment strategy for practical implementation.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2403.00923</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2024-03 |
issn | 2331-8422 |
language | eng |
recordid | cdi_arxiv_primary_2403_00923 |
source | arXiv.org; Free E- Journals |
subjects | Complexity Computer Science - Computation and Language Computer Science - Information Retrieval Data processing Datasets Electronic commerce Graph neural networks Plug & play Searching |
title | An Interpretable Ensemble of Graph and Language Models for Improving Search Relevance in E-Commerce |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-16T20%3A16%3A14IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=An%20Interpretable%20Ensemble%20of%20Graph%20and%20Language%20Models%20for%20Improving%20Search%20Relevance%20in%20E-Commerce&rft.jtitle=arXiv.org&rft.au=Choudhary,%20Nurendra&rft.date=2024-03-01&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2403.00923&rft_dat=%3Cproquest_arxiv%3E2937451775%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2937451775&rft_id=info:pmid/&rfr_iscdi=true |