--- title: "Wee Sun Lee — author profile and papers" description: "Wee Sun Lee, National University of Singapore: 2 papers on Elamur Research (2019–2025), h-index 40 — affiliations, topics, co-authors and who cites them…" canonical: "https://research.elamur.ai/free/en/authors/wee-sun-lee/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/wee-sun-lee/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Wee Sun Lee # Wee Sun Lee Wee Sun Lee works on machine learning for natural language. The papers here follow two lines. One is [aspect-based sentiment analysis](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/), where a system must find the aspects a review mentions and judge the sentiment expressed toward each. The other is the reinforcement-learning training of large language models for mathematical reasoning. Both studies take an established pipeline apart. They ask how its parts interact and which of them actually account for the observed results. The most cited of these papers, [An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/he-2019-interactive-multi-task-learning-network/) (2019), moves away from handling aspect extraction and sentiment classification as consecutive steps, an arrangement in which mistakes propagate and the link between the two subtasks is ignored. It instead builds one network of CNN encoders whose shared latent representation feeds several task-specific components, so that the subtasks can inform each other. The newer direction appears in [Understanding R1-Zero-Like Training: A Critical Perspective](https://md.research.elamur.ai/free/en/papers/liu-2025-understanding-r1-zero-like-training/) (2025). This paper examines the idea of applying reinforcement learning straight to a base model without supervised fine-tuning, and it separates the contribution of the base model from that of the RL algorithm. Testing several base models on MATH training questions, it looks at the effect of prompt templates, at exploration and at self-reflection. It reports that self-reflection is already present before any RL. It also finds that Qwen2.5 models perform best with no template, which hints that question–answer text was part of their pretraining. Lee is based at the [National University of Singapore](https://md.research.elamur.ai/free/en/universities/national-university-of-singapore/), with bylines there from 2002 onward. Earlier papers list the [Australian National University](https://md.research.elamur.ai/free/en/universities/australian-national-university/), the Australian Defence Force Academy, UNSW Canberra and [UNSW Sydney](https://md.research.elamur.ai/free/en/universities/unsw-sydney/). Co-authors on the papers here include [Ruidan He](https://md.research.elamur.ai/free/en/authors/ruidan-he/), [Hwee Tou Ng](https://md.research.elamur.ai/free/en/authors/hwee-tou-ng/), [Daniel Dahlmeier](https://md.research.elamur.ai/free/en/authors/daniel-dahlmeier/) and [Min Lin](https://md.research.elamur.ai/free/en/authors/min-lin/). Wee Sun Lee has 2 papers in our library, in 2019–2025, most of them on [Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/); often with [Daniel Dahlmeier](https://md.research.elamur.ai/free/en/authors/daniel-dahlmeier/), [Hwee Tou Ng](https://md.research.elamur.ai/free/en/authors/hwee-tou-ng/), [Min Lin](https://md.research.elamur.ai/free/en/authors/min-lin/). 2 papers in our library · 2019–2025 [OpenAlex](https://openalex.org/A5071864357) · [**h-index 40**](https://openalex.org/authors/A5071864357) · [141 works](https://openalex.org/works?filter=author.id:A5071864357) · [7,570 citations](https://openalex.org/works?filter=author.id:A5071864357&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/wee-sun-lee/#papers) · [🔗 457 citations in our library](https://md.research.elamur.ai/free/en/authors/wee-sun-lee/cited-by/) · [2 more in our library without a page yet](#also) · [⭐ Paper Star rank #2674](https://md.research.elamur.ai/free/en/paper-stars/page/27/#star-2674) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Wee+Sun+Lee) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Wee+Sun+Lee) · [dblp](https://dblp.org/search?q=Wee+Sun+Lee) · [ACL Anthology](https://aclanthology.org/search/?q=Wee+Sun+Lee) ## Affiliations [🎓**National University of Singapore** Singapore · Singapore 2002–2025 · 99 papers*current*](https://md.research.elamur.ai/free/en/universities/national-university-of-singapore/) · [🎓**Australian Defence Force Academy** Canberra · Australia 1996–2000 · 5 papers](https://ror.org/02j5s7g39) · [🎓**Australian National University** Canberra · Australia 1994–1997 · 5 papers](https://md.research.elamur.ai/free/en/universities/australian-national-university/) · [🏢**Systems, Applications & Products in Data Processing** London · United Kingdom 2017–2019 · 4 papers](https://md.research.elamur.ai/free/en/companies/systems-applications-products-in-data-processing/) · [🎓**UNSW Sydney** Sydney · Australia 1996–1998 · 3 papers](https://md.research.elamur.ai/free/en/universities/unsw-sydney/) · [🎓**UNSW Canberra** Canberra 1997–2000 · 2 papers](https://ror.org/0125wpx05) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed. ## Topics [Sentiment & emotion (1)](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) ## Works by year ### 2020s [**2025** 1 paper](https://md.research.elamur.ai/free/en/papers/liu-2025-understanding-r1-zero-like-training/) ### 2010s [**2019** 1 paper](https://md.research.elamur.ai/free/en/papers/he-2019-interactive-multi-task-learning-network/) ## Papers The most cited first (OpenAlex and our library). 1. **[An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/he-2019-interactive-multi-task-learning-network/)** *(2019 · 348 citations)* Aspect-based sentiment analysis (ABSA) involves finding the aspect terms in a review sentence and deciding which sentiment is expressed toward each one. 2. **[Understanding R1-Zero-Like Training: A Critical Perspective](https://md.research.elamur.ai/free/en/papers/liu-2025-understanding-r1-zero-like-training/)** *(2025 · 266 citations)* DeepSeek-R1-Zero showed that reinforcement learning applied directly to a base LLM, with no SFT stage, can strengthen reasoning. ## Also in our library 2 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 4 co-authors with a page, the most papers together first. - [Daniel Dahlmeier](https://md.research.elamur.ai/free/en/authors/daniel-dahlmeier/) - [Hwee Tou Ng](https://md.research.elamur.ai/free/en/authors/hwee-tou-ng/) - [Min Lin](https://md.research.elamur.ai/free/en/authors/min-lin/) - [Ruidan He](https://md.research.elamur.ai/free/en/authors/ruidan-he/) ## Cited by Papers of our library cite their works 457 times (of the 140,884 papers whose bibliographies we read); [17 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/wee-sun-lee/cited-by/).