Yisong Miao’s Academic Homepage

About

Aloha 👋 You have reached my 1-page style academic homepage.

I am a second year PhD student at WING-SoC-NUS. I study natural language processing with Prof Min-Yen Kan.

Physical Yisong: AS6 Building, meet me in the lab :P
Digital Yisong: [Google Scholar] [LinkedIn] [GitHub] [Twitter] [Skype] [Out-dated 1-page CV]
Email Yisong: [yisong domain-of comp.nus.edu.sg]; [miaoyisong domain-of gmail.com].

I keep a progress log for my research:

My Google Calendar is also available at the end of the page. Carpe Diem!

Table of content:


Research overview

One-sentence SOP: I want to build computational models that understand human’s language in an explainable and intelligent way.

To achieve it, I am studying (have studied) the following topics:

Discourse (2021-)

Discourse concerns the organization of text in a coherent and logical manner. It is a perfect discipline to study language understanding because diverse linguistic devices exist and complex reasoning is required.

The problem is decomposed as: (1) Can we find a computational proxy for understanding discourse? (2) Can we inject intermediate guidance for better understanding? (3) Can we identify key neurons/subnetworks for discourse functions and design a better pretraining strategy?

Here is a longer version for my SOP. We have a paper under submission. Please contact me if you’re interested in reading it!

Emoji (2021-)

Emojis inspire people to text creatively. People compose several emojis together to express a new meaning. For example:

🐻‍❄️=🐻+🧊, where 🐻‍❄️ is a composition of a bear 🐻 and ice 🧊 (means it is cold).

Standard languages (e.g. English) are the main focus for lexical composition research. We create a new dataset for emoji compositions with their corresponding concept. We also have a model to learn such composition.

This is a FYP project by Zi Yun Yang that I co-advised with Prof Min. We tried to submit a paper to COLING ‘22, but it didn’t make in. We are now revising the paper. Please contact us if you want to read our manuscript.

Conversational recommendation (2018-2020)

Users have a hard time “telling” recommendation systems what they like. Recent advances in dialogue systems unlock new possibilities for user interactions. My co-authored papers in 2020 studied this topic.

Even though I am not studying this topic currently, I wish the these aspects can be considered by our community in the future.


Paper archive

Here is an archive for my (co-)authored conference papers, workshop papers and technical reports.

Some of them belongs to fast research and some to slow research (😛 wiki here from Min’s talk on this concept).

2022

[1] Saurabh Jain, Yisong Miao, Min-Yen Kan, Comparative Snippet Generation. [ 2022.ecnlp-1.7 (@ ACL Anthology) ] [ Poster (.pdf) ] [ Dataset (@ GitHub) ]

2021

[1] Wenqiang Lei, Yisong Miao, Runpeng Xie, Bonnie Webber, Meichun Liu, Tat-Seng Chua and Nancy Chen (2021) Have We Solved The Hard Problem? It’s Not Easy! Contextual Lexical Contrast as a Means to Probe Neural Coherence (AAAI ‘21) [PDF] [Slides] [Poster] [Code and Data] [bib]

[2] Yisong Miao. (2021). Mining and Analyzing Questions from Paper Titles. An Engineering Trial Task. [Slides@Google] [Codebase@GitHub]

[3] Yihao Ang, Yisong Miao* . (*=Ordered Alphabetically) (2021) Towards Molecular-level Similarity Search based on Text Data. An In-Class Project in CS6219, Advanced Topics in Computer Systems. [Slides@here] [Code@GitHub]

[4] Yong Liang Goh* , Yongbin Li* , Yisong Miao*. (*=Ordered Alphabetically) (2021) Connecting the Dots: Explaining Human Reasoning on the Graph. A Case Study on Deep Question Generation. An In-Class Paper in CS6208, Advanced Topics in AI. [PDF] [Code upon request]

2020

[1] Wenqiang Lei, Xiangnan He, Yisong Miao, Qingyun Wu, Richang Hong, Min-Yen Kan, Tat Seng Chua (2020). Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems. In Proceedings of the Thirteenth ACM International Conference on Web Search and Data Mining (WSDM ‘20). [PDF] [Slides] [Poster] [Codes and Project Websites @ Github.io]

[2] Wenqiang Lei, Gangyi Zhang, Xiangnan He, Yisong Miao, Xiang Wang, Liang Chen and Tat-Seng Chua (2020). Interactive Path Reasoning on Graph for Conversational Recommendation. (KDD ‘20). [PDF] [Codes and Project Websites @ Github.io]


Teaching and Mentoring

I list my TAs and mentorships in a reverse chronological order:

TA:

Mentoring:


Service

Program Committee / Reviewer

[… Forgot to record for a long time!]

2022

ACL Rolling Review. EMNLP 2022. AAAI 2023.

Before 2022

Secondary Reviewer


Education

2014-2018, Bachelor of Engineering in Computer Science.
Founding Class of undergrad program of University of Chinese Academy of Sciences.

2018-2020, Master of Computing, National University of Singapore.
Thesis advisor: Min-Yen Kan. I learned a ton of knowledge from Wenqiang Lei about dialogue/discourse and conversational recommendation. I also consulted my research to Xiangnan He, Tat-Seng Chua, and Nancy F. Chen.

2021- , PhD in Computer Science, National University of Singapore.
Thesis advisor: Min-Yen Kan.

Calendar

🔝 Go back to top

------ Stay Hungry, Stay Foolish ------