[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-187770-en":3,"doc-seo-187770-105":30,"detail-sidebar-cat-1-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":11,"category_id":12,"category_name":13,"doc_title":14,"doc_description":15,"doc_content":16,"file_id":17,"file_url":18,"file_type":19,"file_size":20,"view_count":4,"is_deleted":4,"is_public":11,"is_downloadable":11,"audit_status":11,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":15,"update_tm":28,"read_time":29},187770,2336475401981,"Chumphorn","https://ap-avatar.wpscdn.com/avatar/22000c94efd8d5204d?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786935347598174694",1,158,"General","2024 EACL SRW 11","This document presents performance metrics for different models, including \"SSMlarge\" and \"SSMsmall\", compared against a \"Gold\" standard. The metrics evaluated are Contr. Precision, Contr. Recall, Entail. Precision, Entail. Recall, Neutr. Precision, Neutr. Recall, Accuracy, Avg. F1-Score, and Cohen’s Kappa. Additionally, the document shows similarity scores using Cosine S., Jaccard S., and BERTScore for the same models. The \"Gold\" standard consistently achieves higher scores across most precision and recall metrics, indicating superior performance. For similarity scores, the \"Gold\" standard also leads in Cosine S. and BERTScore, while \"SSMsmall\" slightly outperforms \"SSMlarge\" in Jaccard S. This comparative analysis appears to be part of a research paper or conference proceeding, likely focusing on natural language processing or machine learning model evaluation.","| Metric | Gold | SSMlarge | SSMsmall |\n| --- | --- | --- | --- |\n| Contr. Precision | 0.949 | 0.763 | 0.713 |\n| Contr. Recall | 0.899 | 0.286 | 0.576 |\n| Entail. Precision | 0.968 | 0.619 | 0.667 |\n| Entail. Recall | 0.704 | 0.549 | 0.573 |\n| Neutr. Precision | 0.485 | 0.242 | 0.299 |\n| Neutr. Recall | 0.887 | 0.630 | 0.528 |\n| Accuracy | 0.807 | 0.468 | 0.556 |\n| Avg. F1-Score | 0.788 | 0.449 | 0.545 |\n| Cohen’s Kappa | 0.709 | 0.219 | 0.339 |\n\n\n| Model | Cosine S. | Jaccard S. | BERTScore |\n| --- | --- | --- | --- |\n| Gold | 0.808 | 0.277 | 0.604 |\n| SSMlarge | 0.771 | 0.182 | 0.455 |\n| SSMsmall | 0.779 | 0.196 | 0.463 |","cbCailJih2QpLo32","https://ap.wps.com/l/cbCailJih2QpLo32","pdf",1238603,14,"English","en",105,"# Performance Metrics\n## Similarity Scores","[{\"question\":\"What are the key performance metrics evaluated in this document?\",\"answer\":\"The key performance metrics include Contr. Precision, Contr. Recall, Entail. Precision, Entail. Recall, Neutr. Precision, Neutr. Recall, Accuracy, Avg. F1-Score, and Cohen’s Kappa.\"},{\"question\":\"Which model performed best according to the evaluated metrics?\",\"answer\":\"The \\\"Gold\\\" standard model generally performed best across most precision and recall metrics, as well as in Cosine S. and BERTScore similarity measures.\"},{\"question\":\"How were the similarity scores calculated?\",\"answer\":\"Similarity scores were calculated using three methods: Cosine S., Jaccard S., and BERTScore, comparing the \\\"Gold\\\" standard against \\\"SSMlarge\\\" and \\\"SSMsmall\\\" models.\"}]","2024 EACL SRW 11 | PDF",1788385313,5,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":14,"keywords":34,"description":15,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"2024-eacl-srw-11","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":11},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/template/","Template",2,{"item":49,"name":13,"@type":43,"position":50},"https://docshare.wps.com/template/general/",3,{"item":52,"name":14,"@type":43,"position":53},"https://docshare.wps.com/template/2024-eacl-srw-11/187770/",4,{"url":52,"name":14,"@type":55,"author":56,"headline":14,"publisher":58,"fileFormat":61,"inLanguage":23,"description":15,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-09-06","2026-09-02",true,{"@type":66,"interactionType":67,"userInteractionCount":47},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What are the key performance metrics evaluated in this document?","Question",{"text":76,"@type":77},"The key performance metrics include Contr. Precision, Contr. Recall, Entail. Precision, Entail. Recall, Neutr. Precision, Neutr. Recall, Accuracy, Avg. F1-Score, and Cohen’s Kappa.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which model performed best according to the evaluated metrics?",{"text":81,"@type":77},"The \"Gold\" standard model generally performed best across most precision and recall metrics, as well as in Cosine S. and BERTScore similarity measures.",{"name":83,"@type":74,"acceptedAnswer":84},"How were the similarity scores calculated?",{"text":85,"@type":77},"Similarity scores were calculated using three methods: Cosine S., Jaccard S., and BERTScore, comparing the \"Gold\" standard against \"SSMlarge\" and \"SSMsmall\" models.","https://schema.org",{"og:url":52,"og:type":88,"og:title":14,"og:site_name":59,"og:description":15},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,99,104,108,113,118,123,128,132],{"id":95,"doc_module":11,"doc_module_name":46,"category_name":96,"show_sort_weight":97,"slug":98},11,"Presentations",90,"presentations",{"id":100,"doc_module":11,"doc_module_name":46,"category_name":101,"show_sort_weight":102,"slug":103},12,"Resumes",80,"resumes",{"id":21,"doc_module":11,"doc_module_name":46,"category_name":105,"show_sort_weight":106,"slug":107},"Invoices",70,"invoices",{"id":109,"doc_module":11,"doc_module_name":46,"category_name":110,"show_sort_weight":111,"slug":112},15,"Posters",60,"posters",{"id":114,"doc_module":11,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},16,"Social Media",50,"social-media",{"id":119,"doc_module":11,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},17,"Forms",40,"forms",{"id":124,"doc_module":11,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},18,"Letters",30,"letters",{"id":129,"doc_module":11,"doc_module_name":46,"category_name":130,"show_sort_weight":29,"slug":131},21,"Paper Templates","papers-templates",{"id":12,"doc_module":11,"doc_module_name":46,"category_name":13,"show_sort_weight":4,"slug":133},"general-158"]