[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-182243-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-182243-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","rnmtkg-transe","RNMT+KG (TransE)","","This document presents a comparative analysis of different machine translation models, including RNMT and Transformer-based architectures, enhanced with Knowledge Graphs (KGs). It details the performance metrics such as BLEU scores for various KG embedding methods (TransE, TransH, TransR) and language pairs (CH)EN. The research highlights the 'Our method' which achieves superior results in multiple metrics, indicating the effectiveness of KG integration. Specifically, the Transformer+KG (TransE) model shows promising improvements over baseline methods. The document also includes data on Medical, Tourism, and General categories, suggesting a broad applicability of the studied techniques. The findings are presented in tabular format, allowing for direct comparison of different models and their respective scores.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/rnmtkg-transe/182243/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/rnmtkg-transe/182243.png","ImageObject",300,407,{"name":42,"@type":43},"Dozel","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-29","2026-09-02",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",14,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What is the primary focus of this document?","Question",{"text":63,"@type":64},"The document focuses on comparing the performance of different machine translation models, particularly those enhanced with Knowledge Graphs (KGs).","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Which models are compared in this study?",{"text":68,"@type":64},"The study compares RNMT and Transformer-based models, including variations with KG integration using different embedding methods like TransE, TransH, and TransR.",{"name":70,"@type":61,"acceptedAnswer":71},"What do the results suggest about the \"Our method\"?",{"text":72,"@type":64},"The results indicate that \"Our method\" generally outperforms the baseline models across various metrics, highlighting the benefit of KG integration in machine translation.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},182243,1788347775,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":107,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":80,"read_time":144,"preview_page_count":4},962085662650,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","| \u003Cbr>药品(yaopin)\u003Cbr>KG\u003Cbr>type\u003Cbr>s\u003Cbr>alias\u003Cbr>\u003Cbr>type\u003Cbr>\u003Cbr>乙酰水杨酸\u003Cbr>(yixianshuiyangsuan)\u003Cbr>阿司匹林（asipilin） |  | \u003Cbr>type\u003Cbr>\u003Cbr>drug\u003Cbr>KG t\u003Cbr>aspirin |\n| --- | --- | --- |\n|  |  |  |\n|  |  |  |\n\n| CH)EN | 2.01M | Medical (0.38M/0.23M) | 2000/2000 |\n| --- | --- | --- | --- |\n|  |  | Tourism (0.16M/0.28M) | 2000/2000 |\n|  |  | General (3.1M/2.5M) | 919/3870 |\n\n\n| Baselines |  |  |  |  |  |  |  |  |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| 1 | RNMT [Luong et al., 2015] | 12.23 | 11.25 12.94 | 11.89 | 43.96 | 41.34 | 25.47 | 27.43 |\n| 2 | Transformer [Vaswani et al., 2017] | 14.73 | 14.57 14.92 | 13.98 | 45.80 | 44.40 | 27.34 | 29.50 |\n| 3 | Transformer+RC [Lu et al., 2018] | 14.92 | 14.79 14.91 | 14.11 | 46.20 | 44.83 | 27.61 | 29.83 |\n|  |  |  | Our method |  |  |  |  |  |\n| 4 | RNMT+KG (TransE) | 13.66y | 12.54y 13.88y | 12.77y | 44.68y | 41.89􀀃 | 25.84􀀃 | 27.91􀀃 |\n| 5 | RNMT+KG (TransH) | 13.71y | 12.37y 13.84y | 12.84y | 44.49􀀃 | 41.56 | 26.12􀀃 | 27.73 |\n| 6 | RNMT+KG (TransR) | 13.58y | 12.29y 13.79y | 12.99y | 44.54y | 41.77􀀃 | 25.88􀀃 | 28.03􀀃 |\n| 7 | Transformer+KG (TransE) | 15.96y | 15.69y 15.58􀀃 | 14.88y | 46.36􀀃 | 44.91y | 27.79􀀃 | 30.10􀀃 |\n| 8 | Transformer+KG (TransH) | 16.09y | 15.43y 15.77y | 14.69y | 46.48y | 44.80y | 28.01y | 29.88􀀃 |\n| 9 | Transformer+KG (TransR) | 15.70y | 15.54y 15.81y | 14.94y | 46.49y | 44.80y | 27.81􀀃 | 30.17􀀃 |\n\n| RNMT | 13.25 | 9.96 |\n| --- | --- | --- |\n| RNMT+KG | 13.54 | 11.75 |\n\n\n| Transformer | 21.5%(31) | 25.2%(31) | 36.5%(35) |\n| --- | --- | --- | --- |\n| Transformer+RC | 21.5%(31) | 25.2%(31) | 43. 8%(42) |\n| Ours | 31.3%(45) | 26. 8%(33) | 36.5%(35) |","cbCaienLndKTLPqc","https://ap.wps.com/l/cbCaienLndKTLPqc","pdf",661301,"English","# Baselines\n## RNMT\n## Transformer\n## Transformer+RC\n## Ours","[{\"question\":\"What is the primary focus of this document?\",\"answer\":\"The document focuses on comparing the performance of different machine translation models, particularly those enhanced with Knowledge Graphs (KGs).\"},{\"question\":\"Which models are compared in this study?\",\"answer\":\"The study compares RNMT and Transformer-based models, including variations with KG integration using different embedding methods like TransE, TransH, and TransR.\"},{\"question\":\"What do the results suggest about the \\\"Our method\\\"?\",\"answer\":\"The results indicate that \\\"Our method\\\" generally outperforms the baseline models across various metrics, highlighting the benefit of KG integration in machine translation.\"}]","RNMT+KG (TransE) | PDF",18]