--- title: "Haoyang Wen — author profile and papers" description: "Haoyang Wen, Amazon: 2 papers on Elamur Research (2019–2023), h-index 10 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/haoyang-wen/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/haoyang-wen/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Haoyang Wen # Haoyang Wen Haoyang Wen has 2 papers in our library, in 2019–2023, most of them on [Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/), [Speech & spoken language](https://md.research.elamur.ai/free/en/topics/speech/); often with [Libo Qin](https://md.research.elamur.ai/free/en/authors/libo-qin/), [Ting Liu](https://md.research.elamur.ai/free/en/authors/ting-liu/), [Wanxiang Che](https://md.research.elamur.ai/free/en/authors/wanxiang-che/). 2 papers in our library · 2019–2023 [OpenAlex](https://openalex.org/A5036195690) · [**h-index 10**](https://openalex.org/authors/A5036195690) · [22 works](https://openalex.org/works?filter=author.id:A5036195690) · [596 citations](https://openalex.org/works?filter=author.id:A5036195690&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/haoyang-wen/#papers) · [🔗 96 citations in our library](https://md.research.elamur.ai/free/en/authors/haoyang-wen/cited-by/) · [1 more in our library without a page yet](#also) · [⭐ Paper Star rank #3205](https://md.research.elamur.ai/free/en/paper-stars/page/33/#star-3205) 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=Haoyang+Wen) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Haoyang+Wen) · [dblp](https://dblp.org/search?q=Haoyang+Wen) · [ACL Anthology](https://aclanthology.org/search/?q=Haoyang+Wen) ## Affiliations [🎓**University of Illinois Urbana-Champaign** Urbana · United States 2021–2026 · 11 papers*current*](https://md.research.elamur.ai/free/en/universities/university-of-illinois-urbana-champaign/) · [🏢**Amazon** Seattle · United States 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/companies/amazon/) · [🎓**Carnegie Mellon University** Pittsburgh · United States 2021–2025 · 10 papers](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) · [🎓**Harbin Institute of Technology** Harbin · China 2018–2020 · 7 papers](https://md.research.elamur.ai/free/en/universities/harbin-institute-of-technology/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. ## Topics [Sentiment & emotion (1)](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · [Speech & spoken language (1)](https://md.research.elamur.ai/free/en/topics/speech/) ## Works by year ### 2020s [**2023** 1 paper](https://md.research.elamur.ai/free/en/papers/wen-2023-zero-shot-few-shot-stance/) ### 2010s [**2019** 1 paper](https://md.research.elamur.ai/free/en/papers/qin-2019-stack-propagation-framework-token-level/) ## Papers The most cited first (OpenAlex and our library). 1. **[A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding](https://md.research.elamur.ai/free/en/papers/qin-2019-stack-propagation-framework-token-level/)** *(2019 · 384 citations)* Spoken language understanding (SLU) in task-oriented dialogue combines two linked subtasks: intent detection, which classifies an utterance, and slot filling, which labels its tokens. 2. **[Zero-Shot and Few-Shot Stance Detection on Varied Topics via Conditional Generation](https://md.research.elamur.ai/free/en/papers/wen-2023-zero-shot-few-shot-stance/)** *(2023 · 26 citations)* Stance detection decides whether a text supports, opposes, or is neutral toward a target. The VAST benchmark makes this harder because most test targets appear rarely or never in training. Earlier VAST systems treat the task as classification, learning label vectors from scratch and ignoring the meaning of the label… ## Also in our library 1 more work of theirs is in our library without a page here yet; it will appear as we publish them. ## Co-authors here 3 co-authors with a page, the most papers together first. - [Libo Qin](https://md.research.elamur.ai/free/en/authors/libo-qin/) - [Ting Liu](https://md.research.elamur.ai/free/en/authors/ting-liu/) - [Wanxiang Che](https://md.research.elamur.ai/free/en/authors/wanxiang-che/) ## Cited by Papers of our library cite their works 96 times (of the 140,884 papers whose bibliographies we read); [3 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/haoyang-wen/cited-by/).