Merge pull request #1 from WING-NUS/main

Sync downstream

content/_index.md

@@ -8,13 +8,11 @@ sections:
   - block: hero
     content:
       title: |
-        Wowchemy
-        Research Group
+        Web IR / NLP Group (WING) @ NUS
       image:
         filename: welcome.jpg
       text: |
-        <br>
-        The **Web, Information Retrieval / Natural Language Processing Group (WING)** explores the research area of applied language processing and information retrieval to the Web and related technologies. Areas of current interest are question answering, scholarly digital libraries, verb similarity, focused crawling, citation parsing and spidering, web page classification and division, text segmentation, and full text analysis. WING is headed by A/P Min-Yen KAN. We are based in the Computational Linguistics Laboratory of the School of Computing at the National University of Singapore. We often work with the Natural Language Processing Group and the (Lab for Media Search)[http://lms.comp.nus.edu.sg/]. We are part of the Media Technologies research group umbrella.
+        The <strong>Web, Information Retrieval / Natural Language Processing Group (WING)</strong> explores the research area of applied language processing and information retrieval to the Web and related technologies. Areas of current interest are question answering, scholarly digital libraries, verb similarity, focused crawling, citation parsing and spidering, web page classification and division, text segmentation, and full text analysis. WING is headed by <A HREF="authors/min-yen-kan">Min</a> (A/P Min-Yen KAN). We are based in the Computational Linguistics Laboratory of the <a href="https://www.comp.nus.edu.sg">School of Computing</a> at the National University of Singapore. We often work with the Natural Language Processing Group and the <a href="http://lms.comp.nus.edu.sg/">Lab for Media Search</a>. We are part of the Media Technologies research group umbrella.
   
   - block: collection
     content:
@@ -73,7 +71,7 @@ sections:
       title:
       subtitle:
       text: |
-        {{% cta cta_link="./people/" cta_text="Meet the team →" %}}
+        {{% cta cta_link="./people/" %}}
     design:
       columns: '1'
 ---

content/authors/alumnus/_index.md

@@ -3,8 +3,8 @@
 title: Somebody
 
 # Full Name (for SEO)
-first_name: Min-Yen
-last_name: Kan
+first_name: Somebody
+last_name: Somewhere
 
 # Is this the primary user of the site?
 superuser: false
@@ -14,9 +14,9 @@ superuser: false
 #   For an email link, use "fas" icon pack, "envelope" icon, and a link in the
 #   form "mailto:[email protected]" or "#contact" for contact widget.
 social:
-  - icon: house
-    icon_pack: fas
-    link: https://www.comp.nus.edu.sg/~kanmy/
+  # - icon: house
+  #  icon_pack: fas
+  #  link: https://www.comp.nus.edu.sg/~kanmy/
 
 # Highlight the author in author lists? (true/false)
 highlight_name: false
@@ -27,5 +27,4 @@ user_groups:
   - Alumni
 
 ---
-
 An alumnus

content/authors/jason/_index.md

@@ -0,0 +1,62 @@
+---
+# Display name
+title: Jason Qiu
+
+# Full Name (for SEO)
+first_name: Jason
+last_name: Qiu
+
+# Is this the primary user of the site?
+superuser: true
+
+# Role/position
+role: Undergraduate Student
+
+# Organizations/Affiliations
+organizations:
+  - name: National University of Singapore, School of Computing
+    url: 'http://www.comp.nus.edu.sg'
+
+# Short bio (displayed in user profile at end of posts)
+bio: FYP student
+
+interests:
+  - Artificial Intelligence
+  - Information Retrieval
+
+
+
+
+# Social/Academic Networking
+# For available icons, see: https://docs.hugoblox.com/getting-started/page-builder/#icons
+#   For an email link, use "fas" icon pack, "envelope" icon, and a link in the
+#   form "mailto:[email protected]" or "#contact" for contact widget.
+social:
+  - icon: house
+    icon_pack: fas
+    link: https://www.linkedin.com/in/jasonqiu212/
+  - icon: envelope
+    icon_pack: fas
+    link: 'mailto:[email protected]'
+
+# Link to a PDF of your resume/CV from the About widget.
+# To enable, copy your resume/CV to `static/files/cv.pdf` and uncomment the lines below.
+# - icon: cv
+#   icon_pack: ai
+#   link: files/cv.pdf
+
+# Enter email to display Gravatar (if Gravatar enabled in Config)
+email: '[email protected]'
+
+# Highlight the author in author lists? (true/false)
+highlight_name: false
+
+# Organizational groups that you belong to (for People widget)
+#   Set this to `[]` or comment out if you are not using People widget.
+user_groups:
+  - Undergraduate Students
+#  - Researchers
+---
+
+Jason Qiu is a FYP student joing our group in 2024. 
+

content/authors/min/_index.md

@@ -18,7 +18,7 @@ organizations:
     url: 'http://www.comp.nus.edu.sg'
 
 # Short bio (displayed in user profile at end of posts)
-bio: My research interests include distributed robotics, mobile computing and programmable matter.
+bio: WING lead; interests include Digital Libraries, Information Retrieval and Natural Language Processing. 
 
 interests:
   - Artificial Intelligence
@@ -76,11 +76,11 @@ highlight_name: false
 # Organizational groups that you belong to (for People widget)
 #   Set this to `[]` or comment out if you are not using People widget.
 user_groups:
-  - Principal Investigators
-  - Researchers
+  - Principal Investigator / Staff
+#  - Researchers
 ---
 
-Min-Yen Kan (BS;MS;PhD Columbia Univ.; SACM, SIEEE) is an Associate Professor and Vice Dean of Undergraduate Studies at the National University of Singapore. Min is an active member of the Association of Computational Linguistics (ACL), currently serving as a co-chair for the ACL Ethics Committee, and previously as the ACL Anthology Director (2008–2018). He is an associate editor for Information Retrieval and the survey editor for the Journal of AI Research (JAIR).
+Min-Yen Kan (BS;MS;PhD Columbia Univ.; SACM, SIEEE) is an Associate Professor and Vice Dean of Undergraduate Studies at the National University of Singapore. Min is an active member of the Association of Computational Linguistics (ACL), currently serving as a co-chair for the ACL Ethics Committee (ACL AEC), and previously as the ACL Anthology Director (2008–2018). He is an associate editor for Information Retrieval and the survey editor for the Journal of AI Research (JAIR).
 
 His research interests include digital libraries, natural language processing and information retrieval. He was recognized as a distinguished speaker by the ACM for natural language processing and digital libraries research. Specific projects include work in the areas of scientific discourse analysis, fact verification, full-text literature mining, lexical semantics and large language models. He leads the Web Information Retrieval / Natural Language Processing Group (WING.NUS) http://wing.comp.nus.edu.sg/ 
 

content/people/index.md

@@ -7,20 +7,19 @@ type: landing
 sections:
   - block: people
     content:
-      title: Meet the Team
+      # title: Meet the Team
       # Choose which groups/teams of users to display.
       #   Edit `user_groups` in each user's profile to add them to one or more of these groups.
       user_groups:
-          - Principal Investigators
-          - Staff
+          - Principal Investigator / Staff
           - Graduate Students
           - Undergraduate Students
           - Visitors / Interns
           - Alumni
       sort_by: Params.last_name
       sort_ascending: true
     design:
-      show_interests: false
+      show_interests: true
       show_role: true
       show_social: true
 ---

content/publication/8743365/cite.bib

@@ -0,0 +1,11 @@
+@article{8743365,
+ author = {An, Ya-Hui and Pan, Liangming and Kan, Min-Yen and Dong, Qiang and Fu, Yan},
+ doi = {10.1109/ACCESS.2019.2924250},
+ journal = {IEEE Access},
+ keywords = {Context;Task analysis;Tagging;Message systems;Discussion forums;Context modeling;Semantics;Artificial intelligence;deep learning;hyperlinking;learning resources;MOOC discussion forums;name entity recognition},
+ number = {},
+ pages = {87887-87900},
+ title = {Resource Mention Extraction for MOOC Discussion Forums},
+ volume = {7},
+ year = {2019}
+}

content/publication/8743365/index.md

@@ -0,0 +1,19 @@
+---
+title: Resource Mention Extraction for MOOC Discussion Forums
+authors:
+- Ya-Hui An
+- Liangming Pan
+- min
+- Qiang Dong
+- Yan Fu
+date: '2019-01-01'
+publishDate: '2024-07-12T07:37:44.756935Z'
+publication_types:
+- article-journal
+publication: '*IEEE Access*'
+doi: 10.1109/ACCESS.2019.2924250
+tags:
+- Context;Task analysis;Tagging;Message systems;Discussion forums;Context modeling;Semantics;Artificial
+  intelligence;deep learning;hyperlinking;learning resources;MOOC discussion forums;name
+  entity recognition
+---

content/publication/acl-2017-association-linguistics/cite.bib

@@ -0,0 +1,11 @@
+@proceedings{acl-2017-association-linguistics,
+ address = {Vancouver, Canada},
+ doi = {10.18653/v1/P17-2},
+ editor = {Barzilay, Regina  and
+Kan, Min-Yen},
+ month = {July},
+ publisher = {Association for Computational Linguistics},
+ title = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
+ url = {https://aclanthology.org/P17-2000},
+ year = {2017}
+}

content/publication/acl-2017-association-linguistics/index.md

@@ -0,0 +1,16 @@
+---
+title: 'Proceedings of the 55th Annual Meeting of the Association for Computational
+  Linguistics (Volume 2: Short Papers)'
+authors:
+- Regina Barzilay
+- min
+date: '2017-07-01'
+publishDate: '2024-07-11T07:40:56.389063Z'
+publication_types:
+- book
+publication: '*Association for Computational Linguistics*'
+doi: 10.18653/v1/P17-2
+links:
+- name: URL
+  url: https://aclanthology.org/P17-2000
+---

content/publication/aksu-etal-2021-velocidapter/cite.bib

@@ -0,0 +1,26 @@
+@inproceedings{aksu-etal-2021-velocidapter,
+ abstract = {We introduce a synthetic dialogue generation framework, Velocidapter, which addresses the corpus availability problem for dialogue comprehension. Velocidapter augments datasets by simulating synthetic conversations for a task-oriented dialogue domain, requiring a small amount of bootstrapping work for each new domain. We evaluate the efficacy of our framework on a task-oriented dialogue comprehension dataset, MRCWOZ, which we curate by annotating questions for slots in the restaurant, taxi, and hotel domains of the MultiWOZ 2.2 dataset (Zang et al., 2020). We run experiments within a low-resource setting, where we pretrain a model on SQuAD, fine-tuning it on either a small original data or on the synthetic data generated by our framework. Velocidapter shows significant improvements using both the transformer-based BERTBase and BiDAF as base models. We further show that the framework is easy to use by novice users and conclude that Velocidapter can greatly help training over task-oriented dialogues, especially for low-resourced emerging domains.},
+ address = {Singapore and Online},
+ author = {Aksu, Ibrahim Taha  and
+Liu, Zhengyuan  and
+Kan, Min-Yen  and
+Chen, Nancy},
+ booktitle = {Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue},
+ doi = {10.18653/v1/2021.sigdial-1.14},
+ editor = {Li, Haizhou  and
+Levow, Gina-Anne  and
+Yu, Zhou  and
+Gupta, Chitralekha  and
+Sisman, Berrak  and
+Cai, Siqi  and
+Vandyke, David  and
+Dethlefs, Nina  and
+Wu, Yan  and
+Li, Junyi Jessy},
+ month = {July},
+ pages = {133--143},
+ publisher = {Association for Computational Linguistics},
+ title = {Velocidapter: Task-oriented Dialogue Comprehension Modeling Pairing Synthetic Text Generation with Domain Adaptation},
+ url = {https://aclanthology.org/2021.sigdial-1.14},
+ year = {2021}
+}

content/publication/aksu-etal-2021-velocidapter/index.md

@@ -0,0 +1,32 @@
+---
+title: 'Velocidapter: Task-oriented Dialogue Comprehension Modeling Pairing Synthetic
+  Text Generation with Domain Adaptation'
+authors:
+- Ibrahim Taha Aksu
+- Zhengyuan Liu
+- min  
+- Nancy Chen
+date: '2021-07-01'
+publishDate: '2024-07-05T17:09:42.645613Z'
+publication_types:
+- paper-conference
+publication: '*Proceedings of the 22nd Annual Meeting of the Special Interest Group
+  on Discourse and Dialogue*'
+doi: 10.18653/v1/2021.sigdial-1.14
+abstract: We introduce a synthetic dialogue generation framework, Velocidapter, which
+  addresses the corpus availability problem for dialogue comprehension. Velocidapter
+  augments datasets by simulating synthetic conversations for a task-oriented dialogue
+  domain, requiring a small amount of bootstrapping work for each new domain. We evaluate
+  the efficacy of our framework on a task-oriented dialogue comprehension dataset,
+  MRCWOZ, which we curate by annotating questions for slots in the restaurant, taxi,
+  and hotel domains of the MultiWOZ 2.2 dataset (Zang et al., 2020). We run experiments
+  within a low-resource setting, where we pretrain a model on SQuAD, fine-tuning it
+  on either a small original data or on the synthetic data generated by our framework.
+  Velocidapter shows significant improvements using both the transformer-based BERTBase
+  and BiDAF as base models. We further show that the framework is easy to use by novice
+  users and conclude that Velocidapter can greatly help training over task-oriented
+  dialogues, especially for low-resourced emerging domains.
+links:
+- name: URL
+  url: https://aclanthology.org/2021.sigdial-1.14
+---

content/publication/aksu-etal-2022-n/cite.bib

@@ -0,0 +1,19 @@
+@inproceedings{aksu-etal-2022-n,
+ abstract = {Augmentation of task-oriented dialogues has followed standard methods used for plain-text such as back-translation, word-level manipulation, and paraphrasing despite its richly annotated structure. In this work, we introduce an augmentation framework that utilizes belief state annotations to match turns from various dialogues and form new synthetic dialogues in a bottom-up manner. Unlike other augmentation strategies, it operates with as few as five examples. Our augmentation strategy yields significant improvements when both adapting a DST model to a new domain, and when adapting a language model to the DST task, on evaluations with TRADE and TOD-BERT models. Further analysis shows that our model performs better on seen values during training, and it is also more robust to unseen values. We conclude that exploiting belief state annotations enhances dialogue augmentation and results in improved models in n-shot training scenarios.},
+ address = {Dublin, Ireland},
+ author = {Aksu, Ibrahim  and
+Liu, Zhengyuan  and
+Kan, Min-Yen  and
+Chen, Nancy},
+ booktitle = {Findings of the Association for Computational Linguistics: ACL 2022},
+ doi = {10.18653/v1/2022.findings-acl.131},
+ editor = {Muresan, Smaranda  and
+Nakov, Preslav  and
+Villavicencio, Aline},
+ month = {May},
+ pages = {1659--1671},
+ publisher = {Association for Computational Linguistics},
+ title = {N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking},
+ url = {https://aclanthology.org/2022.findings-acl.131},
+ year = {2022}
+}

content/publication/aksu-etal-2022-n/index.md

@@ -0,0 +1,29 @@
+---
+title: N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking
+authors:
+- Ibrahim Aksu
+- Zhengyuan Liu
+- min
+- Nancy Chen
+date: '2022-05-01'
+publishDate: '2024-07-05T17:09:42.588862Z'
+publication_types:
+- paper-conference
+publication: '*Findings of the Association for Computational Linguistics: ACL 2022*'
+doi: 10.18653/v1/2022.findings-acl.131
+abstract: Augmentation of task-oriented dialogues has followed standard methods used
+  for plain-text such as back-translation, word-level manipulation, and paraphrasing
+  despite its richly annotated structure. In this work, we introduce an augmentation
+  framework that utilizes belief state annotations to match turns from various dialogues
+  and form new synthetic dialogues in a bottom-up manner. Unlike other augmentation
+  strategies, it operates with as few as five examples. Our augmentation strategy
+  yields significant improvements when both adapting a DST model to a new domain,
+  and when adapting a language model to the DST task, on evaluations with TRADE and
+  TOD-BERT models. Further analysis shows that our model performs better on seen values
+  during training, and it is also more robust to unseen values. We conclude that exploiting
+  belief state annotations enhances dialogue augmentation and results in improved
+  models in n-shot training scenarios.
+links:
+- name: URL
+  url: https://aclanthology.org/2022.findings-acl.131
+---

content/publication/aksu-etal-2023-prompter/cite.bib

@@ -0,0 +1,18 @@
+@inproceedings{aksu-etal-2023-prompter,
+ abstract = {A challenge in the Dialogue State Tracking (DST) field is adapting models to new domains without using any supervised data --- zero-shot domain adaptation. Parameter-Efficient Transfer Learning (PETL) has the potential to address this problem due to its robustness. However, it has yet to be applied to the zero-shot scenarios, as it is not clear how to apply it unsupervisedly. Our method, Prompter, uses descriptions of target domain slots to generate dynamic prefixes that are concatenated to the key and values at each layer′s self-attention mechanism. This allows for the use of prefix-tuning in zero-shot. Prompter outperforms previous methods on both the MultiWOZ and SGD benchmarks. In generating prefixes, our analyses find that Prompter not only utilizes the semantics of slot descriptions but also how often the slots appear together in conversation. Moreover, Prompter′s gains are due to its improved ability to distinguish ″none″-valued dialogue slots, compared against baselines.},
+ address = {Toronto, Canada},
+ author = {Aksu, Ibrahim Taha  and
+Kan, Min-Yen  and
+Chen, Nancy},
+ booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
+ doi = {10.18653/v1/2023.acl-long.252},
+ editor = {Rogers, Anna  and
+Boyd-Graber, Jordan  and
+Okazaki, Naoaki},
+ month = {July},
+ pages = {4588--4603},
+ publisher = {Association for Computational Linguistics},
+ title = {Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptation},
+ url = {https://aclanthology.org/2023.acl-long.252},
+ year = {2023}
+}

content/publication/aksu-etal-2023-prompter/index.md

@@ -0,0 +1,29 @@
+---
+title: 'Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptation'
+authors:
+- Ibrahim Taha Aksu
+- min
+- Nancy Chen
+date: '2023-07-01'
+publishDate: '2024-07-06T02:22:24.632344Z'
+publication_types:
+- paper-conference
+publication: '*Proceedings of the 61st Annual Meeting of the Association for Computational
+  Linguistics (Volume 1: Long Papers)*'
+doi: 10.18653/v1/2023.acl-long.252
+abstract: A challenge in the Dialogue State Tracking (DST) field is adapting models
+  to new domains without using any supervised data --- zero-shot domain adaptation.
+  Parameter-Efficient Transfer Learning (PETL) has the potential to address this problem
+  due to its robustness. However, it has yet to be applied to the zero-shot scenarios,
+  as it is not clear how to apply it unsupervisedly. Our method, Prompter, uses descriptions
+  of target domain slots to generate dynamic prefixes that are concatenated to the
+  key and values at each layer′s self-attention mechanism. This allows for the use
+  of prefix-tuning in zero-shot. Prompter outperforms previous methods on both the
+  MultiWOZ and SGD benchmarks. In generating prefixes, our analyses find that Prompter
+  not only utilizes the semantics of slot descriptions but also how often the slots
+  appear together in conversation. Moreover, Prompter′s gains are due to its improved
+  ability to distinguish ″none″-valued dialogue slots, compared against baselines.
+links:
+- name: URL
+  url: https://aclanthology.org/2023.acl-long.252
+---