Added author pages for Kun Zhang: ustc, Inria, ucas

data/xml/2022.coling.xml

@@ -7016,7 +7016,7 @@
     </paper>
     <paper id="533">
       <title>Meta-<fixed-case>CQG</fixed-case>: A Meta-Learning Framework for Complex Question Generation over Knowledge Bases</title>
-      <author><first>Kun</first><last>Zhang</last></author>
+      <author id="kun-zhang-ucas"><first>Kun</first><last>Zhang</last></author>
       <author><first>Yunqi</first><last>Qiu</last></author>
       <author><first>Yuanzhuo</first><last>Wang</last></author>
       <author><first>Long</first><last>Bai</last></author>

data/xml/2022.emnlp.xml

@@ -11009,7 +11009,7 @@
       <title><fixed-case>C</fixed-case>ausal<fixed-case>NLP</fixed-case> Tutorial: An Introduction to Causality for Natural Language Processing</title>
       <author><first>Zhijing</first><last>Jin</last></author>
       <author><first>Amir</first><last>Feder</last></author>
-      <author><first>Kun</first><last>Zhang</last></author>
+      <author id="kun-zhang"><first>Kun</first><last>Zhang</last></author>
       <pages>17-22</pages>
       <abstract>Causal inference is becoming an increasingly important topic in deep learning, with the potential to help with critical deep learning problems such as model robustness, interpretability, and fairness. In addition, causality is naturally widely used in various disciplines of science, to discover causal relationships among variables and estimate causal effects of interest. In this tutorial, we introduce the fundamentals of causal discovery and causal effect estimation to the natural language processing (NLP) audience, provide an overview of causal perspectives to NLP problems, and aim to inspire novel approaches to NLP further. This tutorial is inclusive to a variety of audiences and is expected to facilitate the community’s developments in formulating and addressing new, important NLP problems in light of emerging causal principles and methodologies.</abstract>
       <url hash="ae117c13">2022.emnlp-tutorials.4</url>

data/xml/2022.findings.xml

@@ -4472,7 +4472,7 @@
     <paper id="285">
       <title>Incorporating Dynamic Semantics into Pre-Trained Language Model for Aspect-based Sentiment Analysis</title>
       <author><first>Kai</first><last>Zhang</last></author>
-      <author><first>Kun</first><last>Zhang</last></author>
+      <author id="kun-zhang"><first>Kun</first><last>Zhang</last></author>
       <author><first>Mengdi</first><last>Zhang</last></author>
       <author><first>Hongke</first><last>Zhao</last></author>
       <author><first>Qi</first><last>Liu</last></author>

data/xml/2023.acl.xml

@@ -12781,7 +12781,7 @@
       <author><first>Kun</first><last>Huang</last><affiliation>Nanjing University of Science and Technology</affiliation></author>
       <author><first>Xiaocui</first><last>Yang</last><affiliation>School of Computer Science and Engineering, Northeastern University,</affiliation></author>
       <author><first>Pengfei</first><last>Hong</last><affiliation>Singapore University of Technology and Design</affiliation></author>
-      <author><first>Kun</first><last>Zhang</last><affiliation>Nanjing University of Science and Technology</affiliation></author>
+      <author id="kun-zhang"><first>Kun</first><last>Zhang</last><affiliation>Nanjing University of Science and Technology</affiliation></author>
       <author><first>Soujanya</first><last>Poria</last><affiliation>Singapore University of Technology and Design</affiliation></author>
       <pages>15960-15973</pages>
       <abstract>Document-level relation extraction (DocRE) aims to infer complex semantic relations among entities in a document. Distant supervision (DS) is able to generate massive auto-labeled data, which can improve DocRE performance. Recent works leverage pseudo labels generated by the pre-denoising model to reduce noise in DS data. However, unreliable pseudo labels bring new noise, e.g., adding false pseudo labels and losing correct DS labels. Therefore, how to select effective pseudo labels to denoise DS data is still a challenge in document-level distant relation extraction. To tackle this issue, we introduce uncertainty estimation technology to determine whether pseudo labels can be trusted. In this work, we propose a Document-level distant Relation Extraction framework with Uncertainty Guided label denoising, UGDRE. Specifically, we propose a novel instance-level uncertainty estimation method, which measures the reliability of the pseudo labels with overlapping relations. By further considering the long-tail problem, we design dynamic uncertainty thresholds for different types of relations to filter high-uncertainty pseudo labels. We conduct experiments on two public datasets. Our framework outperforms strong baselines by 1.91 F1 and 2.28 Ign F1 on the RE-DocRED dataset.</abstract>

data/xml/2023.findings.xml

@@ -15270,7 +15270,7 @@
     </paper>
     <paper id="48">
       <title><fixed-case>R</fixed-case>e<fixed-case>FSQL</fixed-case>: A Retrieval-Augmentation Framework for Text-to-<fixed-case>SQL</fixed-case> Generation</title>
-      <author><first>Kun</first><last>Zhang</last></author>
+      <author id="kun-zhang-ucas"><first>Kun</first><last>Zhang</last></author>
       <author><first>Xiexiong</first><last>Lin</last></author>
       <author><first>Yuanzhuo</first><last>Wang</last></author>
       <author><first>Xin</first><last>Zhang</last></author>
@@ -23331,7 +23331,7 @@
     </paper>
     <paper id="672">
       <title><fixed-case>F</fixed-case>act<fixed-case>S</fixed-case>potter: Evaluating the Factual Faithfulness of Graph-to-Text Generation</title>
-      <author><first>Kun</first><last>Zhang</last></author>
+      <author id="kun-zhang-inria"><first>Kun</first><last>Zhang</last></author>
       <author><first>Oana</first><last>Balalau</last></author>
       <author><first>Ioana</first><last>Manolescu</last></author>
       <pages>10025-10042</pages>

data/xml/2024.lrec.xml

@@ -17745,7 +17745,7 @@
       <title>Visual-Linguistic Dependency Encoding for Image-Text Retrieval</title>
       <author><first>Wenxin</first><last>Guo</last></author>
       <author><first>Lei</first><last>Zhang</last></author>
-      <author><first>Kun</first><last>Zhang</last></author>
+      <author id="kun-zhang-ustc"><first>Kun</first><last>Zhang</last></author>
       <author><first>Yi</first><last>Liu</last></author>
       <author><first>Zhendong</first><last>Mao</last></author>
       <pages>17384–17396</pages>

data/xml/P19.xml

@@ -480,7 +480,7 @@
       <author><first>Mingxiao</first><last>An</last></author>
       <author><first>Fangzhao</first><last>Wu</last></author>
       <author><first>Chuhan</first><last>Wu</last></author>
-      <author><first>Kun</first><last>Zhang</last></author>
+      <author id="kun-zhang-ustc"><first>Kun</first><last>Zhang</last></author>
       <author><first>Zheng</first><last>Liu</last></author>
       <author><first>Xing</first><last>Xie</last></author>
       <pages>336–345</pages>

data/yaml/name_variants.yaml

@@ -10720,6 +10720,18 @@
   id: r-thomas-mccoy
   variants:
   - {first: Tom, last: McCoy}
+- canonical: {first: Kun, last: Zhang}
+  comment: University of Science and Technology of China
+  id: kun-zhang-ustc
+- canonical: {first: Kun, last: Zhang}
+  comment: Inria Saclay-Île-de-France
+  id: kun-zhang-inria
+- canonical: {first: Kun, last: Zhang}
+  comment: University of Chinese Academy of Sciences
+  id: kun-zhang-ucas
+- canonical: {first: Kun, last: Zhang}
+  comment: May refer to multiple people
+  id: kun-zhang
 - canonical: {first: Xuan Long, last: Do}
   variants:
   - {first: Do Xuan, last: Long}