update

2023-07-18 10:12:48 +03:00 · 2022-10-22 02:59:45 +08:00
parent 5b1b805847
commit b4033bda01
14 changed files with 312 additions and 10 deletions
--- a/.DS_Store
+++ b/.DS_Store
--- a/.idea/GenKBC_Papers.iml
+++ b/.idea/GenKBC_Papers.iml
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>
--- a/.idea/inspectionProfiles/profiles_settings.xml
+++ b/.idea/inspectionProfiles/profiles_settings.xml
@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>
--- a/.idea/misc.xml
+++ b/.idea/misc.xml
@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8" project-jdk-type="Python SDK" />
+</project>
--- a/.idea/modules.xml
+++ b/.idea/modules.xml
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/GenKBC_Papers.iml" filepath="$PROJECT_DIR$/.idea/GenKBC_Papers.iml" />
+    </modules>
+  </component>
+</project>
--- a/.idea/vcs.xml
+++ b/.idea/vcs.xml
@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>
--- a/.idea/workspace.xml
+++ b/.idea/workspace.xml
@@ -1,7 +1,10 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <project version="4">
  <component name="ChangeListManager">
-    <list default="true" id="16338359-5063-4a6a-9257-7b8e6356e990" name="Changes" comment="" />
+    <list default="true" id="16338359-5063-4a6a-9257-7b8e6356e990" name="Changes" comment="">
+      <change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/README.md" beforeDir="false" afterPath="$PROJECT_DIR$/README.md" afterDir="false" />
+    </list>
    <option name="SHOW_DIALOG" value="false" />
    <option name="HIGHLIGHT_CONFLICTS" value="true" />
    <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
@@ -19,14 +22,14 @@
    <option name="hideEmptyMiddlePackages" value="true" />
    <option name="showLibraryContents" value="true" />
  </component>
-  <component name="PropertiesComponent"><![CDATA[{
-  "keyToString": {
-    "RunOnceActivity.OpenProjectViewOnStart": "true",
-    "RunOnceActivity.ShowReadmeOnStart": "true",
-    "WebServerToolWindowFactoryState": "false",
-    "last_opened_file_path": "/Users/admin/Documents/GitHub/GenKBC_Papers"
+  <component name="PropertiesComponent">{
+  &quot;keyToString&quot;: {
+    &quot;RunOnceActivity.OpenProjectViewOnStart&quot;: &quot;true&quot;,
+    &quot;RunOnceActivity.ShowReadmeOnStart&quot;: &quot;true&quot;,
+    &quot;WebServerToolWindowFactoryState&quot;: &quot;false&quot;,
+    &quot;last_opened_file_path&quot;: &quot;/Users/admin/Documents/GitHub/GenKBC_Papers&quot;
  }
-}]]></component>
+}</component>
  <component name="SpellCheckerSettings" RuntimeDictionaries="0" Folders="0" CustomDictionaries="0" DefaultDictionary="application-level" UseSingleDictionary="true" transferred="true" />
  <component name="TaskManager">
    <task active="true" id="Default" summary="Default task">
@@ -37,7 +40,9 @@
      <updated>1663412949494</updated>
      <workItem from="1663412952649" duration="108000" />
      <workItem from="1663595570665" duration="4000" />
-      <workItem from="1665726550749" duration="1694000" />
+      <workItem from="1665726550749" duration="1735000" />
+      <workItem from="1666338687396" duration="132000" />
+      <workItem from="1666338853458" duration="11572000" />
    </task>
    <servers />
  </component>
--- a/Blank-based.png
+++ b/Blank-based.png
--- a/Copy-based.png
+++ b/Copy-based.png
--- a/Indice-based.png
+++ b/Indice-based.png
--- a/Label-based.png
+++ b/Label-based.png
--- a/README.md
+++ b/README.md
@@ -10,6 +10,268 @@
 **[:bell: News! :bell: ]
 We have released a new survey paper based on this repository, with a perspective of existing Generative Knowledge Graph Construction! We are looking forward to any comments or discussions on this topic :)** 

+## 🕵️ Introduction
+Generative Knowledge Graph Construction (KGC) refers to those methods that leverage the sequence-to-sequence framework for building knowledge graphs, which is flexible and can be adapted to widespread tasks.
+In this study, we summarize the recent compelling progress in generative knowledge graph construction. 
+We present the advantages and weaknesses of each paradigm in terms of different generation targets and provide theoretical insight and empirical analysis. 
+Based on the review, we suggest promising research directions for the future. Our contributions are threefold: (1) We present a detailed, complete taxonomy for the generative KGC methods; 
+(2) We provide a theoretical and empirical analysis of the generative KGC methods; 
+(3) We propose several research directions that can be developed in the future.
+
+## *👋 News!*
+- Congratulations! Our work has been accepted by the EMNLP2022 main conference.
+- We will release our paper on arivx soon!
+
+## 🏳‍🌈 A Taxonomy of Current Methods
+
+In this Survey, we summarize recent progress in generative KGC. We propose to organize relevant work by the generation target of models and also present the axis of the task level.
+
+
+<p align='center'>
+    </br>
+    <img src='Taxonomy.png' width='1000'>
+</p>
+
+
+### 1. Copy-based Sequence.
+This paradigm refers to developing more robust models to copy the corresponding entity directly from the input sentence during the generation process. 
+As shown in figure, the model copies the head entity from the input sentence and then the tail entity.
+
+<p align='center'>
+    </br>
+    <img src='Copy-based.png' width='500'>
+</p>
+
+- ***Directly copy entity***
+  - **"Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism"**, ACL 2018
+    - Xiangrong Zeng, Daojian Zeng, Shizhu He, Kang Liu, Jun Zhao
+    - [[Paper]](https://aclanthology.org/P18-1047/)
+
+  - **"Learning the Extraction Order of Multiple Relational Facts in a Sentence with Reinforcement Learning"**, AAAI 2020
+    - Xiangrong Zeng, Shizhu He, Daojian Zeng, Kang Liu, Shengping Liu, Jun Zhao
+    - [[Paper]](https://doi.org/10.18653/v1/D19-1035)
+
+  - **"CopyMTL: Copy Mechanism for Joint Extraction of Entities and Relations with Multi-Task Learning"**, EMNLP 2019
+    - Daojian Zeng, Haoran Zhang, Qianying Liu
+    - [[Paper]](https://ojs.aaai.org/index.php/AAAI/article/view/6495)
+
+  - **"Document-level Entity-based Extraction as Template Generation"**, EMNLP 2021
+    - Kung-Hsiang Huang, Sam Tang, Nanyun Peng
+    - [[Paper]](https://aclanthology.org/2021.emnlp-main.426/)
+    
+- ***Restricted target vocabulary***
+  - **"A sequence-to-sequence approach for document-level relation extraction"**,  BioNLP 2022
+    - John Giorgi, Gary Bader, Bo Wang
+    - [[Paper]](https://aclanthology.org/2022.bionlp-1.2/)
+
+### 2. Structure-linearized Sequence.
+This paradigm refers to utilizing structural knowledge and label semantics, making it prone to handling a unified output format.
+As shown in figure, the output is a linearization of the extracted knowledge structure.
+<p align='center'>
+    </br>
+    <img src='Structure-linearized.png' width='500'>
+</p>
+
+- ***Per-token tag encoding***
+  - **"Exploring Sequence-to-Sequence Learning in Aspect Term Extraction"**, ACL 2019
+    - Dehong Ma, Sujian Li, Fangzhao Wu, Xing Xie, Houfeng Wang
+    - [[Paper]](https://aclanthology.org/P19-1344/)
+
+  - **"Neural Architectures for Nested NER through Linearization"**, ACL 2019
+    - Jana Straková, Milan Straka, Jan Hajic
+    - [[Paper]](https://aclanthology.org/P19-1527/)
+
+- ***Faithful contrastive learning***
+
+  - **"Contrastive Triple Extraction with Generative Transformer"**, AAAI 2021
+    - Hongbin Ye, Ningyu Zhang, Shumin Deng, Mosha Chen, Chuanqi Tan, Fei Huang, Huajun Chen
+    - [[Paper]](https://ojs.aaai.org/index.php/AAAI/article/view/17677/)
+  
+  - **"Contrastive Triple Extraction with Generative Transformer"**, IEEE ACM Trans. Audio Speech Lang. Process
+    - Ningyu Zhang, Hongbin Ye, Shumin Deng, Chuanqi Tan, Mosha Chen, Songfang Huang, Fei Huang, Huajun Chen
+    - [[Paper]](https://ieeexplore.ieee.org/document/9537684)
+
+  - **"Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning"**, ACL 2022
+    - Swarnadeep Saha, Prateek Yadav, Mohit Bansal
+    - [[Paper]](https://aclanthology.org/2022.acl-long.85/)
+    
+
+- ***Prefix tree constraint decoding***
+
+  - **"Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction"**, ACL 2021
+    - Yaojie Lu, Hongyu Lin, Jin Xu, Xianpei Han, Jialong Tang, Annan Li, Le Sun, Meng Liao, Shaoyi Chen
+    - [[Paper]](https://aclanthology.org/2021.acl-long.217/)
+
+  
+- ***Triplet linearization***
+
+  - **"REBEL: Relation Extraction By End-to-end Language generation"**, EMNLP 2021
+    - Pere-Lluís Huguet Cabot, Roberto Navigli
+    - [[Paper]](https://aclanthology.org/2021.findings-emnlp.204/)
+
+  - **"De-Bias for Generative Extraction in Unified NER Task"**, ACL 2022
+    - Shuai Zhang, Yongliang Shen, Zeqi Tan, Yiquan Wu, Weiming Lu
+    - [[Paper]](https://aclanthology.org/2022.acl-long.59/)
+
+- ***Entity-aware hierarchical decoding***
+
+  - **"From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer"**, WWW 2022
+    - Xin Xie, Ningyu Zhang, Zhoubo Li, Shumin Deng, Hui Chen, Feiyu Xiong, Mosha Chen, Huajun Chen
+    - [[Paper]](https://doi.org/10.1145/3487553.3524238)
+
+- ***Unified structure generation***
+
+  - **"Unified Structure Generation for Universal Information Extraction"**, ACL 2022
+    - Yaojie Lu, Qing Liu, Dai Dai, Xinyan Xiao, Hongyu Lin, Xianpei Han, Le Sun, Hua Wu
+    - [[Paper]](https://aclanthology.org/2022.acl-long.395/)
+    
+  - **"DeepStruct: Pretraining of Language Models for Structure Prediction"**, ACL 2022
+    - Chenguang Wang, Xiao Liu, Zui Chen, Haoyun Hong, Jie Tang, Dawn Song
+    - [[Paper]](https://aclanthology.org/2022.findings-acl.67/)
+
+
+- ***Reformulating triple prediction***
+
+  - **"Intent Classification and Slot Filling for Privacy Policies"**, ACL 2021
+    - Wasi Uddin Ahmad, Jianfeng Chi, Tu Le, Thomas Norton, Yuan Tian, Kai-Wei Chang
+    - [[Paper]](https://aclanthology.org/2021.acl-long.340/)
+
+  - **"HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extraction"**, ACL 2021
+    - Liliang Ren, Chenkai Sun, Heng Ji, Julia Hockenmaier
+    - [[Paper]](https://aclanthology.org/2021.findings-acl.356/)
+
+  - **"SQUIRE: A Sequence-to-sequence Framework for Multi-hop Knowledge Graph Reasoning"**, EMNLP 2022
+    - Yushi Bai, Xin Lv, Juanzi Li, Lei Hou, Yincen Qu, Zelin Dai, Feiyu Xiong
+    - [[Paper]](https://arxiv.org/abs/2201.06206)
+
+
+
+- ***Query Verbalization***
+
+  - **"Improving Candidate Retrieval with Entity Profile Generation for Wikidata Entity Linking"**, ACL 2022
+    - Tuan Lai, Heng Ji, ChengXiang Zhai
+    - [[Paper]](https://aclanthology.org/2022.findings-acl.292/)
+
+  - **"Sequence-to-Sequence Knowledge Graph Completion and Question Answering"**, ACL 2022
+    - Apoorv Saxena, Adrian Kochsiek, Rainer Gemulla
+    - [[Paper]](https://aclanthology.org/2022.acl-long.201/)
+
+  - **"Knowledge Is Flat: A Seq2Seq Generative Framework for Various Knowledge Graph Completion"**, COLING 2022
+    - Chen Chen, Yufei Wang, Bing Li, Kwok-Yan Lam
+    - [[Paper]](https://arxiv.org/abs/2209.07299)
+
+### 3. Label-based Sequence.
+This paradigm refers to utilizing the extra markers to indicate specific entities or relationships.
+As shown in figure, the output sequence copies all words in the input sentence, as it helps to reduce ambiguity.
+In addition, this paradigm uses square brackets or other identifiers to specify the tagging sequence for the entity of interest. 
+The relevant labels are separated by the separator "$|$" within enclosed brackets. 
+Meanwhile, the labeled words are described with natural words so that the potential knowledge of the pre-trained model can be leveraged.
+<p align='center'>
+    </br>
+    <img src='Label-based.png' width='500'>
+</p>
+
+- ***Augmented natural language***
+
+  - **"Augmented Natural Language for Generative Sequence Labeling"**, EMNLP 2020
+    - Ben Athiwaratkun, Cicero Nogueira dos Santos, Jason Krone, Bing Xiang
+    - [[Paper]](https://doi.org/10.18653/v1/2020.emnlp-main.27)
+
+  - **"Autoregressive Entity Retrieval "**, ICLR 2021
+    - Nicola De Cao, Gautier Izacard, Sebastian Riedel, Fabio Petroni
+    - [[Paper]](https://openreview.net/forum?id=5k8F6UU39V)
+
+  - **"Structured Prediction as Translation between Augmented Natural Languages "**, ICLR 2021
+    - Giovanni Paolini, Ben Athiwaratkun, Jason Krone, Jie Ma, Alessandro Achille, RISHITA ANUBHAI, Cicero Nogueira dos Santos, Bing Xiang, Stefano Soatto
+    - [[Paper]](https://openreview.net/forum?id=US-TP-xnXI)
+
+
+
+### 4. Indice-based Sequence.
+This paradigm generates the indices of the words in the input text of interest directly, and encodes class labels as label indices.
+As the output is strictly restricted, it will not generate indices that corresponding entities do not exist in the input text, except for relation labels.
+
+<p align='center'>
+    </br>
+    <img src='Indice-based.png' width='500'>
+</p>
+
+- ***Pointer mechanism***
+
+  - **"Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation Extraction Authors"**, AAAI 2020
+    - Tapas Nayak, Hwee Tou Ng
+    - [[Paper]](https://ojs.aaai.org/index.php/AAAI/article/view/6374)
+
+  - **"Don’t Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsing"**, WWW 2020
+    - Subendhu Rongali, Luca Soldaini, Emilio Monti, Wael Hamza
+    - [[Paper]](https://dl.acm.org/doi/10.1145/3366423.3380064)
+
+  - **"A Unified Generative Framework for Various NER Subtasks"**, ACL 2021
+    - Hang Yan, Tao Gui, Junqi Dai, Qipeng Guo, Zheng Zhang, Xipeng Qiu
+    - [[Paper]](https://aclanthology.org/2021.acl-long.451/)
+
+  - **"A Unified Generative Framework for Aspect-based Sentiment Analysis"**, ACL 2021
+    - Hang Yan, Junqi Dai, Tuo Ji, Xipeng Qiu, Zheng Zhang
+    - [[Paper]](https://aclanthology.org/2021.acl-long.188/)
+
+- ***Pointer selection***
+
+  - **"GRIT: Generative Role-filler Transformers for Document-level Event Entity Extraction"**, EACL 2021
+    - Xinya Du, Alexander Rush, Claire Cardie
+    - [[Paper]](https://aclanthology.org/2021.eacl-main.52/)
+
+
+### 5. Blank-based Sequence.
+This paradigm refers to utilizing templates to define the appropriate order and relationship for the generated spans.
+As shown in figure,  the template refers to a text describing an event type, which adds blank argument role placeholders.
+The output sequences are sentences where the blank placeholders are replaced by specific event arguments. 
+
+<p align='center'>
+    </br>
+    <img src='Blank-based.png' width='500'>
+</p>
+
+- ***Template filling as generation***
+
+  - **"COMET: Commonsense Transformers for Automatic Knowledge Graph Construction"**, ACL 2019
+    - Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Celikyilmaz, Yejin Choi
+    - [[Paper]](https://aclanthology.org/P19-1470/)
+
+  - **"Document-Level Event Argument Extraction by Conditional Generation"**, NAACL 2021
+    - Sha Li, Heng Ji, Jiawei Han
+    - [[Paper]](https://aclanthology.org/2021.naacl-main.69/)
+
+  - **"Template Filling with Generative Transformers"**, NAACL 2021
+    - Xinya Du, Alexander Rush, Claire Cardie
+    - [[Paper]](https://aclanthology.org/2021.naacl-main.70/)
+
+  - **"ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification"**, ACL 2022
+    - Yucheng Zhou, Tao Shen, Xiubo Geng, Guodong Long, Daxin Jiang
+    - [[Paper]](https://aclanthology.org/2022.acl-long.183/)
+
+- ***Prompt semantic guidance***
+
+  - **"DEGREE: A Data-Efficient Generation-Based Event Extraction Model"**, NAACL 2022
+    - I-Hung Hsu, Kuan-Hao Huang, Elizabeth Boschee, Scott Miller, Prem Natarajan, Kai-Wei Chang, Nanyun Peng
+    - [[Paper]](http://arxiv.org/abs/2108.12724)
+
+  - **"Dynamic Prefix-Tuning for Generative Template-based Event Extraction"**, ACL 2022
+    - Xiao Liu, Heyan Huang, Ge Shi, Bo Wang
+    - [[Paper]](https://aclanthology.org/2022.acl-long.358/)
+
+  - **"Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction"**, ACL 2022
+    - Yubo Ma, Zehao Wang, Yixin Cao, Mukai Li, Meiqi Chen, Kun Wang, Jing Shao
+    - [[Paper]](https://aclanthology.org/2022.acl-long.466/)
+
+- ***Language-agnostic template***
+
+  - **"Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction"**, ACL 2022
+    - Kuan-Hao Huang, I-Hung Hsu, Prem Natarajan, Kai-Wei Chang, Nanyun Peng
+    - [[Paper]](https://aclanthology.org/2022.acl-long.317)
+
+
+
+## 🏆 A List of Survey Papers

 | Survey Paper                                                                                                                       |  Publish   |
 |:-----------------------------------------------------------------------------------------------------------------------------------|:----------:|
@@ -18,6 +280,9 @@ We have released a new survey paper based on this repository, with a perspective
 | [Multi-Modal Knowledge Graph Construction and Application: A Survey](https://arxiv.org/abs/2202.05786)                             | Arxiv 2022 |
 | [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://arxiv.org/abs/2111.01243) | Arxiv 2021 |

+## 🕚 A Timeline of generative KGC. 
+The time for each paper is based on its first arXiv version (if exists) or estimated submission time. 
+

 | Papers                                                                                                                                                                                                                                    |           Method           | Conference  |                                  Code                                  |
 |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------:|:-----------:|:----------------------------------------------------------------------:|
@@ -59,7 +324,7 @@ We have released a new survey paper based on this repository, with a perspective
 | [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://aclanthology.org/P19-1470/)                                                                                                                                  |             Blank-based           |  ACL 2019   |       [COMET](https://github.com/atcbosselut/comet-commonsense)        |
 | [Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism](https://aclanthology.org/P18-1047/)                                                                                                                               |            Copy-based            |  ACL 2018   |                                   -                                    |

-## TIPS
+## 🌟 TIPS
 If you find this repository useful to your research or work, it is really appreciate to star this repository. 


--- a/Structure-linearized.png
+++ b/Structure-linearized.png
--- a/Taxonomy.png
+++ b/Taxonomy.png