Add Dan Zhang (Tsinghua) (#4404)

bin/requirements.txt

@@ -5,8 +5,9 @@ click
 docopt>=0.6.0
 filelock==3.15.1
 filetype
+GitPython==3.1.44
 iso-639
-langcodes[data]
+langcodes[data]==3.5.0
 latexcodec>=1.0.7
 lxml>=4.2.0
 msgspec
@@ -22,9 +23,10 @@ PyYAML>=3.0
 requests
 rich
 ruff~=0.3.4
-stop-words
+setuptools==75.6.0
+stop-words==2018.7.23
 texsoup~=0.3.1
 tqdm
 wheel>=0.33.4
-PyGithub
+PyGithub==2.5.0
 -e python/

data/xml/2022.dash.xml

@@ -21,7 +21,7 @@
     </frontmatter>
     <paper id="1">
       <title><fixed-case>MEGA</fixed-case>nno: Exploratory Labeling for <fixed-case>NLP</fixed-case> in Computational Notebooks</title>
-      <author><first>Dan</first><last>Zhang</last><affiliation>Megagon Labs</affiliation></author>
+      <author id="dan-zhang"><first>Dan</first><last>Zhang</last><affiliation>Megagon Labs</affiliation></author>
       <author><first>Hannah</first><last>Kim</last><affiliation>Megagon Labs</affiliation></author>
       <author><first>Rafael</first><last>Li Chen</last><affiliation>Megagon Labs</affiliation></author>
       <author><first>Eser</first><last>Kandogan</last><affiliation>Megagon Labs</affiliation></author>

data/xml/2022.emnlp.xml

@@ -2649,7 +2649,7 @@
       <title>Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language Model</title>
       <author><first>Mingqi</first><last>Li</last><affiliation>Clemson University</affiliation></author>
       <author><first>Fei</first><last>Ding</last><affiliation>Clemson University</affiliation></author>
-      <author><first>Dan</first><last>Zhang</last><affiliation>Clemson University</affiliation></author>
+      <author id="dan-zhang"><first>Dan</first><last>Zhang</last><affiliation>Clemson University</affiliation></author>
       <author><first>Long</first><last>Cheng</last><affiliation>Clemson University</affiliation></author>
       <author><first>Hongxin</first><last>Hu</last><affiliation>University at Buffalo, SUNY</affiliation></author>
       <author><first>Feng</first><last>Luo</last><affiliation>Clemson University</affiliation></author>

data/xml/2022.findings.xml

@@ -12363,7 +12363,7 @@ Faster and Smaller Speech Translation without Quality Compromise</title>
     <paper id="235">
       <title>Low-resource Interactive Active Labeling for Fine-tuning Language Models</title>
       <author><first>Seiji</first><last>Maekawa</last><affiliation>Osaka University</affiliation></author>
-      <author><first>Dan</first><last>Zhang</last><affiliation>Megagon Labs</affiliation></author>
+      <author id="dan-zhang"><first>Dan</first><last>Zhang</last><affiliation>Megagon Labs</affiliation></author>
       <author><first>Hannah</first><last>Kim</last><affiliation>Megagon Labs</affiliation></author>
       <author><first>Sajjadur</first><last>Rahman</last><affiliation>Megagon Labs</affiliation></author>
       <author><first>Estevam</first><last>Hruschka</last><affiliation>Megagon Labs - https://megagon.ai/</affiliation></author>

data/xml/2023.bionlp.xml

@@ -593,7 +593,7 @@
     <paper id="47">
       <title><fixed-case>D</fixed-case>eakin<fixed-case>NLP</fixed-case> at <fixed-case>P</fixed-case>rob<fixed-case>S</fixed-case>um 2023: Clinical Progress Note Summarization with Rules and Language <fixed-case>M</fixed-case>odels<fixed-case>C</fixed-case>linical Progress Note Summarization with Rules and Languague Models</title>
       <author><first>Ming</first><last>Liu</last><affiliation>Deakin University</affiliation></author>
-      <author><first>Dan</first><last>Zhang</last><affiliation>Deakin University</affiliation></author>
+      <author id="dan-zhang"><first>Dan</first><last>Zhang</last><affiliation>Deakin University</affiliation></author>
       <author><first>Weicong</first><last>Tan</last><affiliation>Monash University</affiliation></author>
       <author><first>He</first><last>Zhang</last><affiliation>Cnpiec Kexin Ltd</affiliation></author>
       <pages>491-496</pages>

data/xml/2024.acl.xml

@@ -13444,7 +13444,7 @@
     <paper id="20">
       <title><fixed-case>A</fixed-case>uto<fixed-case>RE</fixed-case>: Document-Level Relation Extraction with Large Language Models</title>
       <author><first>Lilong</first><last>Xue</last></author>
-      <author><first>Dan</first><last>Zhang</last></author>
+      <author id="dan-zhang-tsinghua"><first>Dan</first><last>Zhang</last></author>
       <author><first>Yuxiao</first><last>Dong</last><affiliation>Tsinghua University</affiliation></author>
       <author><first>Jie</first><last>Tang</last><affiliation>Tsinghua University, Tsinghua University</affiliation></author>
       <pages>211-220</pages>

data/xml/2024.eacl.xml

@@ -3089,7 +3089,7 @@
       <author><first>Kushan</first><last>Mitra</last><affiliation>Megagon Labs</affiliation></author>
       <author><first>Rafael</first><last>Li Chen</last><affiliation>Megagon Labs</affiliation></author>
       <author><first>Sajjadur</first><last>Rahman</last><affiliation>Megagon Labs</affiliation></author>
-      <author><first>Dan</first><last>Zhang</last><affiliation>Megagon Labs</affiliation></author>
+      <author id="dan-zhang"><first>Dan</first><last>Zhang</last><affiliation>Megagon Labs</affiliation></author>
       <pages>168-176</pages>
       <abstract>Large language models (LLMs) can label data faster and cheaper than humans for various NLP tasks. Despite their prowess, LLMs may fall short in understanding of complex, sociocultural, or domain-specific context, potentially leading to incorrect annotations. Therefore, we advocate a collaborative approach where humans and LLMs work together to produce reliable and high-quality labels. We present MEGAnno+, a human-LLM collaborative annotation system that offers effective LLM agent and annotation management, convenient and robust LLM annotation, and exploratory verification of LLM labels by humans.</abstract>
       <url hash="629984d8">2024.eacl-demo.18</url>

data/yaml/name_variants.yaml

@@ -1,3 +1,9 @@
+- canonical: {first: Dan, last: Zhang}
+  id: dan-zhang-tsinghua
+  comment: Tsinghua University
+- canonical: {first: Dan, last: Zhang}
+  id: dan-zhang
+  comment: May refer to several people
 - canonical: {first: Vanja M., last: Karan}
   variants:
   - {first: Vanja Mladen, last: Karan}