Merge pull request #4 from WING-NUS/main

Sync from downstream.

content/authors/thushari/_index.md

@@ -0,0 +1,68 @@
+---
+# Display name
+title: Thushari Pahalage
+
+# Full Name (for SEO)
+first_name: Thushari
+last_name: Pahalage
+
+# Is this the primary user of the site?
+superuser: false
+
+# Role/position
+role: Research Intern
+
+# Organizations/Affiliations
+organizations:
+  - name: University of Lorraine
+    url: 'https://genial.univ-lorraine.fr/'
+
+# Short bio (displayed in user profile at end of posts)
+bio: Research Intern
+
+interests:
+  - Machine Learning
+  - Natural Language Processing
+  - Explainable AI
+  - Cloud Computing
+
+education:
+  courses:
+    - course: Erasmus Mundus Joint Masters Degree in Green Networking And Cloud computing
+      institution: University of Lorraine, Leeds Beckett University, Luleå University of Technology
+      year: 2023
+    - course: B.Tech in Software Engineering
+      institution: Delhi Technological University
+      year: 2019
+
+# 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: envelope
+    icon_pack: fas
+    link: 'mailto:[email protected]'
+  - icon: github
+    icon_pack: fab
+    link: https://github.com/thushariii
+# 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:
+  - Visitors / Interns
+#  - Researchers
+---
+
+Thushari Pahalage is a Research Intern in WING Research Group and working for 2 months starting from July 2024. She is currently enrolled in the Erasmus Mundus Joint Masters Degree program in Green Networking And Cloud computing.

content/authors/victor/_index.md

@@ -0,0 +1,73 @@
+---
+# Display name
+title: Chuang Li 
+
+# Full Name (for SEO)
+first_name: Chuang
+last_name: Li
+
+# Is this the primary user of the site?
+superuser: true
+
+# Role/position
+role: Graduate Students
+
+# 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: PhD Candidate August 2020 Intake
+
+interests:
+  - Information Retrieval
+  - Conversational Recommender System
+  - Large Language Models
+
+education:
+  courses:
+    - course: PhD in Computer Science
+      institution: National University of Singapore
+      year: 2020-2024
+    - course: BSc in Electrical and Computer Engineering
+      institution: National University of Singapore
+      year: 2016-2020
+
+# 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://lichuangnus.github.io
+  - icon: envelope
+    icon_pack: fas
+    link: 'mailto:[email protected]'
+  - icon: google-scholar
+    icon_pack: ai
+    link: https://scholar.google.com/citations?user=_9Q_D1MAAAAJ&hl=en
+  - icon: github
+    icon_pack: fab
+    link: https://github.com/lichuangnus
+# 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:
+  - Graduate Students
+#  - Researchers
+---
+
+Victor is a 4-th year PhD Candidate jointly supervised by Professor Kan Min-Yen and Professor Li Haizhou. His reserach interestes are in Conversational Recommender System and Natural Language Processing. 

content/authors/yisong/_index.md

@@ -0,0 +1,75 @@
+---
+# Display name
+title: Yisong Miao
+
+# Full Name (for SEO)
+first_name: Yisong
+last_name: Miao
+
+# Is this the primary user of the site?
+superuser: true
+
+# Role/position
+role: Graduate Students
+
+# 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: PhD Candidate January 2021 Intake
+
+interests:
+  - Discourse Semantics
+  - Lexical Semantics
+
+education:
+  courses:
+    - course: PhD in Computer Science
+      institution: National University of Singapore
+      year: 2021-Now
+    - course: Master of Computing
+      institution: National University of Singapore
+      year: 2018-2020
+    - course: Bachelor of Computing
+      institution: University of Chinese Academy of Sciences
+      year: 2014-2018
+
+# 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://yisong.me
+  - icon: envelope
+    icon_pack: fas
+    link: 'mailto:[email protected]'
+  - icon: google-scholar
+    icon_pack: ai
+    link: http://scholar.google.com/citations?user=a-oIKBoAAAAJ&hl=en
+  - icon: github
+    icon_pack: fab
+    link: https://github.com/yisongmiao
+# 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:
+  - Graduate Students
+#  - Researchers
+---
+
+Yisong is a fourth-year PhD student under the supervision of Prof. Min-Yen Kan. His research interests include discourse and lexical semantics. He [composes emojis](https://yisong.me/publications/[email protected]) to represent lexical compositions and [asks questions](https://yisong.me/publications/acl24-DiSQ-CR.pdf) to evaluate language models' faithful understanding of discourse relations.

content/publication/acl24discursive/cite.bib

@@ -0,0 +1,7 @@
+@inproceedings{acl24a,
+  title={Discursive Socratic Questioning: Evaluating the Faithfulness of Language Models’ Understanding of Discourse Relations},
+  author={Yisong Miao , Hongfu Liu, Wenqiang Lei, Nancy F. Chen, and Min-Yen Kan},
+  booktitle={Proceedings of the Annual Meeting fof the Association of Computational Linguistics},
+  year={2024},
+  organization={ACL}
+}

content/publication/acl24discursive/index.md

@@ -0,0 +1,61 @@
+---
+title: 'Discursive Socratic Questioning: Evaluating the Faithfulness of Language Models’ Understanding of Discourse Relations'
+# Yisong Miao , Hongfu Liu, Wenqiang Lei, Nancy F. Chen and Min-Yen Kan (2024) Beyond Memorization: The Challenge of Random Memory Access in Language Models. In Proceedings of the Annual Meeting fof the Association of Computational Linguistics (ACL '24).
+
+authors:
+  - yisong
+  - Hongfu Liu
+  - Wenqiang Lei
+  - Nancy F. Chen
+  - min
+
+date: '2024-08-11T00:00:00Z'
+doi: ''
+
+# Schedule page publish date (NOT publication's date).
+publishDate: '2017-01-01T00:00:00Z'
+publication_types: ['paper-conference']
+
+# Publication name and optional abbreviated publication name.
+publication: In *Proceedings of the Annual Meeting fof the Association of Computational Linguistics*
+publication_short: In *ACL 2024*
+
+abstract: While large language models have significantly enhanced the effectiveness of discourse relation classifications, it remains unclear whether their comprehension is faithful and reliable. We provide DiSQ, a new method for evaluating the faithfulness of understanding discourse based on question answering. We first employ in-context learning to annotate the reasoning for discourse comprehension, based on the connections among key events within the discourse. Following this, DiSQ interrogates the model with a sequence of questions to assess its grasp of core event relations, its resilience to counterfactual queries, as well as its consistency to its previous responses. We then evaluate language models with different architectural designs using DiSQ, finding: (1) DiSQ presents a significant challenge for all models, with the top-performing GPT model attaining only 41% of the ideal performance in PDTB; (2) DiSQ is robust to domain shifts and paraphrase variations; (3) Open-source models generally lag behind their closed-source GPT counterparts, with notable exceptions being those enhanced with chat and code/math features; (4) Our analysis validates the effectiveness of explicitly signalled discourse connectives, the role of contextual information, and the benefits of using historical QA data.
+
+# Summary. An optional shortened abstract.
+summary: We propose Discursive Socratic Questioning (DiSQ), a new evaluation measure for discourse semantics. Inspired by the Socratic method, DiSQ involves asking models about key event relations, testing their robustness to counterfactuals, and ensuring consistency with equivalent questions. Experiments show that GPT-4 achieves only 41% of the DiSQ scores. We recommend using context and discourse connectives as essential linguistic features to enhance discourse comprehension.
+
+tags: [nlp]
+
+# Display this page in the Featured widget?
+featured: true
+
+# Custom links (uncomment lines below)
+# links:
+# - name: Custom Link
+#   url: http://example.org
+
+url_pdf: 'https://yisong.me/publications/acl24-DiSQ-CR.pdf'
+url_code: 'https://github.com/YisongMiao/DiSQ-Score'
+
+# Featured image
+# To use, add an image named `featured.jpg/png` to your page's folder.
+image:
+  caption: 'DiSQ combines three discourse-relevant scores: (1) Targeted Score, gauging responses to key events; (2) Counterfactual Score, assessing robustness against irrelevant queries; (3) Consistency Score, measuring logical coherence to equivalent questions.'
+  preview_only: false
+
+# Associated Projects (optional).
+#   Associate this publication with one or more of your projects.
+#   Simply enter your project's folder or file name without extension.
+#   E.g. `internal-project` references `content/project/internal-project/index.md`.
+#   Otherwise, set `projects: []`.
+projects:
+  - example
+
+# Slides (optional).
+#   Associate this publication with Markdown slides.
+#   Simply enter your slide deck's filename without extension.
+#   E.g. `slides: "example"` references `content/slides/example/index.md`.
+#   Otherwise, set `slides: ""`.
+# slides: example
+---

content/publication/lreccoling24elco/cite.bib

@@ -0,0 +1,20 @@
+@inproceedings{yang-etal-2024-elco-dataset,
+    title = "The {ELC}o Dataset: Bridging Emoji and Lexical Composition",
+    author = "Yang, Zi Yun  and
+      Zhang, Ziqing  and
+      Miao, Yisong",
+    editor = "Calzolari, Nicoletta  and
+      Kan, Min-Yen  and
+      Hoste, Veronique  and
+      Lenci, Alessandro  and
+      Sakti, Sakriani  and
+      Xue, Nianwen",
+    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
+    month = may,
+    year = "2024",
+    address = "Torino, Italia",
+    publisher = "ELRA and ICCL",
+    url = "https://aclanthology.org/2024.lrec-main.1381",
+    pages = "15899--15909",
+    abstract = "Can emojis be composed to convey intricate meanings like English phrases? As a pioneering study, we present the Emoji-Lexical Composition (ELCo) dataset, a new resource that offers parallel annotations of emoji sequences corresponding to English phrases. Our dataset contains 1,655 instances, spanning 209 diverse concepts from tangible ones like {``}right man{''} (✔️👨) to abstract ones such as {``}full attention{''} (🧐✍️, illustrating a metaphoric composition of a focusing face and writing hand). ELCo enables the analysis of the patterns shared between emoji and lexical composition. Through a corpus study, we discovered that simple strategies like direct representation and reduplication are sufficient for conveying certain concepts, but a richer, metaphorical strategy is essential for expressing more abstract ideas. We further introduce an evaluative task, Emoji-based Textual Entailment (EmoTE), to assess the proficiency of NLP models in comprehending emoji compositions. Our findings reveals the challenge of understanding emoji composition in a zero-shot setting for current models, including ChatGPT. Our analysis indicates that the intricacy of metaphorical compositions contributes to this challenge. Encouragingly, models show marked improvement when fine-tuned on the ELCo dataset, with larger models excelling in deciphering nuanced metaphorical compositions.",
+}

content/publication/lreccoling24elco/index.md

@@ -0,0 +1,59 @@
+---
+title: 'The ELCo Dataset: Bridging Emoji and Lexical Composition'
+# Zi Yun Yang, Ziqing Zhang, and Yisong Miao (2024) The ELCo Dataset: Bridging Emoji and Lexical Composition. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING '24).
+
+authors:
+  - Zi Yun Yang
+  - Ziqing Zhang
+  - yisong
+
+date: '2024-05-20T00:00:00Z'
+doi: ''
+
+# Schedule page publish date (NOT publication's date).
+publishDate: '2017-01-01T00:00:00Z'
+publication_types: ['paper-conference']
+
+# Publication name and optional abbreviated publication name.
+publication: In *In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation*
+publication_short: In *LREC-COLING 2024*
+
+abstract: Can emojis be composed to convey intricate meanings like English phrases? As a pioneering study, we present the Emoji-Lexical Composition (ELCo) dataset, a new resource that offers parallel annotations of emoji sequences corresponding to English phrases. Our dataset contains 1,655 instances, spanning 209 diverse concepts from tangible ones like {``}right man{''} (✔️👨) to abstract ones such as {``}full attention{''} (🧐✍️, illustrating a metaphoric composition of a focusing face and writing hand). ELCo enables the analysis of the patterns shared between emoji and lexical composition. Through a corpus study, we discovered that simple strategies like direct representation and reduplication are sufficient for conveying certain concepts, but a richer, metaphorical strategy is essential for expressing more abstract ideas. We further introduce an evaluative task, Emoji-based Textual Entailment (EmoTE), to assess the proficiency of NLP models in comprehending emoji compositions. Our findings reveals the challenge of understanding emoji composition in a zero-shot setting for current models, including ChatGPT. Our analysis indicates that the intricacy of metaphorical compositions contributes to this challenge. Encouragingly, models show marked improvement when fine-tuned on the ELCo dataset, with larger models excelling in deciphering nuanced metaphorical compositions.
+
+# Summary. An optional shortened abstract.
+summary: Can emojis convey intricate meanings like English phrases? We present the Emoji-Lexical Composition (ELCo) dataset with 1,655 instances spanning 209 concepts, from tangible to abstract ideas. ELCo enables analysis of emoji and lexical composition. Our Emoji-based Textual Entailment (EmoTE) task reveals challenges for current models, but fine-tuning improves performance significantly.
+
+tags: [nlp]
+
+# Display this page in the Featured widget?
+featured: true
+
+# Custom links (uncomment lines below)
+# links:
+# - name: Custom Link
+#   url: http://example.org
+
+url_pdf: 'https://aclanthology.org/2024.lrec-main.1381'
+url_code: 'https://github.com/WING-NUS/ELCo'
+
+# Featured image
+# To use, add an image named `featured.jpg/png` to your page's folder.
+image:
+  caption: 'A summary of the ELCo project. The ELCo dataset is comprised of 1,655 annotations of 209 EN phrases 45 adjectives and 77 attributes. Our corpus study reveals five structures to compose emoji compositions, and we show metaphorical structures use more diverse emojis. Our new EmoTE task is challenging for all models, but fine-tuning on ELCo helps to learn useful emoji composition skills. '
+  preview_only: false
+
+# Associated Projects (optional).
+#   Associate this publication with one or more of your projects.
+#   Simply enter your project's folder or file name without extension.
+#   E.g. `internal-project` references `content/project/internal-project/index.md`.
+#   Otherwise, set `projects: []`.
+projects:
+  - example
+
+# Slides (optional).
+#   Associate this publication with Markdown slides.
+#   Simply enter your slide deck's filename without extension.
+#   E.g. `slides: "example"` references `content/slides/example/index.md`.
+#   Otherwise, set `slides: ""`.
+# slides: example
+---