<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Representation-Learning on</title><link>https://h30306.github.io/blog/zh-tw/tags/representation-learning/</link><description>Recent content in Representation-Learning on</description><generator>Hugo -- gohugo.io</generator><language>zh-tw</language><managingEditor>hwork0511@gmail.com (Wei Yi Chung)</managingEditor><webMaster>hwork0511@gmail.com (Wei Yi Chung)</webMaster><copyright>© 2026 Wei Yi Chung</copyright><lastBuildDate>Sun, 06 Feb 2022 00:00:00 +0000</lastBuildDate><atom:link href="https://h30306.github.io/blog/zh-tw/tags/representation-learning/index.xml" rel="self" type="application/rss+xml"/><item><title>碩士論文：基於實體表徵學習與密度估計於指代消解</title><link>https://h30306.github.io/blog/zh-tw/paper/2022-master-thesis-coreference-resolution/</link><pubDate>Sun, 06 Feb 2022 00:00:00 +0000</pubDate><author>hwork0511@gmail.com (Wei Yi Chung)</author><guid>https://h30306.github.io/blog/zh-tw/paper/2022-master-thesis-coreference-resolution/</guid><description>在 SpanBERT 指代消解模型上加入實體表徵估計、群內密度與群間密度三個組件，F1 提升約 0.9</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://h30306.github.io/blog/paper/2022-master-thesis-coreference-resolution/featured.png"/></item></channel></rss>