{"id":491,"date":"2022-09-05T23:24:00","date_gmt":"2022-09-05T15:24:00","guid":{"rendered":"http:\/\/140.115.70.194:6417\/?p=491"},"modified":"2024-09-18T16:31:58","modified_gmt":"2024-09-18T08:31:58","slug":"ensemble-pre-trained-transformer-models-for-writing-style-change-detection","status":"publish","type":"post","link":"https:\/\/ainlp.tw\/index.php\/2022\/09\/05\/ensemble-pre-trained-transformer-models-for-writing-style-change-detection\/","title":{"rendered":"Ensemble Pre-trained Transformer Models for Writing Style Change Detection"},"content":{"rendered":"\n<p>Tzu-Mi Lin, Chao-Yi Chen, Yu-Wen Tzeng and Lung-Hao Lee. <\/p>\n\n\n\n<p>In\u00a0<em>Proceedings of the Working Notes of\u00a0<strong>CLEF 2022<\/strong>\u00a0&#8211; Conference and Labs of the Evaluation Forum<\/em>,  3180, pages 2565-2573.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity is-style-wide\"\/>\n\n\n\n<div style=\"height:20px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p class=\"has-medium-font-size\"><strong>Abstract<\/strong><\/p>\n\n\n\n<p style=\"font-size:clamp(14px, 0.875rem + ((1vw - 3.2px) * 0.156), 16px);\">This paper describes a proposed system design for Style Change Detection (SCD) tasks for PAN at CLEF 2022. We propose a unified architecture of ensemble neural networks to solve three SCD- 2022 edition tasks. We fine-tune the BERT, RoBERTa and ALBERT transformers and their connecting classifiers to measure the similarity of two given paragraphs or sentences for authorship analysis. Each transformer model is regarded as a standalone method to detect differences in the writing styles of each testing pair. The final output prediction is then combined using the majority voting ensemble mechanism. For SCD-2022 Task 1, which requires finding the only one position of a single style at the paragraph level, our approach achieves a macro F1-score of 0.7540. For SCD-2022 Task 2 to detect the actual authors of each written paragraph, our method achieves a macro F1-score of 0.5097, a Diarization error rate of 0.1941 and a Jaccard error rate of 0.3095. For SCD-2022 Task 3 to find located writing style changes at the sentence level, our model achieves a macro F1-score of 0.7156. In summary, our method is the winning approach in the list of all intrinsic approaches.<\/p>\n\n\n\n<div style=\"height:20px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<figure class=\"wp-block-image aligncenter size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"382\" src=\"http:\/\/140.115.70.194:6417\/wp-content\/uploads\/2023\/12\/\u622a\u5716-2023-12-29-\u4e0b\u534811.25.37-1024x382.png\" alt=\"\" class=\"wp-image-492\" srcset=\"https:\/\/ainlp.tw\/wp-content\/uploads\/2023\/12\/\u622a\u5716-2023-12-29-\u4e0b\u534811.25.37-1024x382.png 1024w, https:\/\/ainlp.tw\/wp-content\/uploads\/2023\/12\/\u622a\u5716-2023-12-29-\u4e0b\u534811.25.37-300x112.png 300w, https:\/\/ainlp.tw\/wp-content\/uploads\/2023\/12\/\u622a\u5716-2023-12-29-\u4e0b\u534811.25.37-768x286.png 768w, https:\/\/ainlp.tw\/wp-content\/uploads\/2023\/12\/\u622a\u5716-2023-12-29-\u4e0b\u534811.25.37-1536x573.png 1536w, https:\/\/ainlp.tw\/wp-content\/uploads\/2023\/12\/\u622a\u5716-2023-12-29-\u4e0b\u534811.25.37.png 1920w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>Tzu-Mi Lin, Chao-Yi Chen, Yu-Wen Tzeng and Lung-Hao Lee<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_themeisle_gutenberg_block_has_review":false,"footnotes":""},"categories":[6],"tags":[35,31],"class_list":["post-491","post","type-post","status-publish","format-standard","hentry","category-achievements","tag-35","tag-clef"],"blocksy_meta":[],"_links":{"self":[{"href":"https:\/\/ainlp.tw\/index.php\/wp-json\/wp\/v2\/posts\/491","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ainlp.tw\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ainlp.tw\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ainlp.tw\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/ainlp.tw\/index.php\/wp-json\/wp\/v2\/comments?post=491"}],"version-history":[{"count":2,"href":"https:\/\/ainlp.tw\/index.php\/wp-json\/wp\/v2\/posts\/491\/revisions"}],"predecessor-version":[{"id":793,"href":"https:\/\/ainlp.tw\/index.php\/wp-json\/wp\/v2\/posts\/491\/revisions\/793"}],"wp:attachment":[{"href":"https:\/\/ainlp.tw\/index.php\/wp-json\/wp\/v2\/media?parent=491"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ainlp.tw\/index.php\/wp-json\/wp\/v2\/categories?post=491"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ainlp.tw\/index.php\/wp-json\/wp\/v2\/tags?post=491"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}