知识花园 (Knowledge Garden)

The Knowledge Mining team $\sqsubseteq$ The Websoft research group

您的足迹:

courses:ke

差别

这里会显示出您选择的修订版和当前版本之间的差别。

到此差别页面的链接

--- courses:ke [2026/02/25 09:22] – whu
+++ courses:ke [2026/05/04 13:14] (当前版本) – whu
@@ 行 46: / 行 46: @@
 将提供一批经典论文，并对这些论文提出一些导向性问题。学生需要自选阅读论文，结合对论文的提问，在课堂研讨中对论文的内容进行概述，并对论文中自己特别有体会的地方进行深入阐述。
-**论文挑选规则.** 两人一组，根据报告人学号尾数按 mod 3 的余数选择论文主题；每个主题内的论文可以自由选择；每组报告时长为 15 分钟，外加两分钟问答；课堂进行研讨。
+**论文挑选规则.** 两人一组，根据报告人学号尾数按 mod 3 的余数选择论文主题；每个主题内的论文可以自由选择；每组报告时长为 12 分钟，外加两分钟问答；课堂进行研讨。
-  * **第一次课堂研讨的论文:** x 月 xx 日
+  * **第一次课堂研讨的论文:** 4 月 21 日
     * 知识抽取 (//报告人学号尾数 mod 3 = 0//)
-      *
+      * Improving Distantly-Supervised Relation Extraction with Joint Label Embedding
+      * Double Graph Based Reasoning for Document-level Relation Extraction
+      * GoLLIE: Annotation Guidelines Improve Zero-Shot Information-Extraction
     * 知识库构建 (//报告人学号尾数 mod 3 = 1//)
-      *
+      * DBpedia: A Nucleus for a Web of Open Data
-    * 语言模型 (//报告人学号尾数 mod 3 = 2//)
+      * Knowledge Vault: A Web-Scale Approach to Probabilistic Knowledge Fusion
-      *
+      * Probase: A Probabilistic Taxonomy for Text Understanding
+    * 语言模型知识增强 (//报告人学号尾数 mod 3 = 2//)
+      * KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
+      * ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
+      * WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization
-  * **第二次课堂研讨的论文:** x 月 xx 日
+  * **第二次课堂研讨的论文:** 6 月 9 日
     * 搜索推荐 (//报告人学号尾数 mod 3 = 0//)
-      *
+      * Fielded Sequential Dependence Model for Ad-Hoc Entity Retrieval in the Web of Data
+      * What Links Alice and Bob?: Matching and Ranking Semantic Patterns in Heterogeneous Networks
+      * LLMRec: Large Language Models with Graph Augmentation for Recommendation
     * 知识融合 (//报告人学号尾数 mod 3 = 1//)
-      *
+      * PARIS: Probabilistic Alignment of Relations, Instances, and Schema
+      * Deep Learning for Entity Matching: A Design Space Exploration
+      * HoloClean: Holistic Data Repairs with Probabilistic Inference
     * 机器问答 (//报告人学号尾数 mod 3 = 2//)
-      *
+      * Answering Natural Language Questions by Subgraph Matching over Knowledge Graphs
+      * Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings
+      * Triad: A Framework Leveraging a Multi-Role LLM-based Agent to Solve Knowledge Base Question Answering
 ----

courses/ke.1771982537.txt.gz · 最后更改: 2026/02/25 09:22 由 whu