--- title: "Xiaojun Quan — author profile and papers" description: "Xiaojun Quan, Sun Yat-sen University: 3 papers on Elamur Research (2020–2021), h-index 29 — affiliations, topics, co-authors and who cites them in our…" canonical: "https://research.elamur.ai/free/en/authors/xiaojun-quan/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/xiaojun-quan/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Xiaojun Quan # Xiaojun Quan Xiaojun Quan works in natural language processing. Their papers here deal with sentiment and emotion in text and with dialogue systems. A recurring question is how to give neural models the right structure to draw on: syntactic relations within a sentence, the order of turns in a conversation, or the shared hierarchy of dialogue acts. Graph-based networks are the common method across these works, which fall under [Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) and [Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) and also touch on [speech act theory](https://md.research.elamur.ai/free/en/topics/speech-act-theory/). The most cited of Quan's papers here is [Relational Graph Attention Network for Aspect-based Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/wang-2020-relational-graph-attention-network-aspect/) (2020). It targets reviews in which a single sentence mentions several aspects with conflicting opinions. Attention alone can pair an aspect with the wrong opinion word, so the paper brings in syntactic structure tailored to the task. Also from 2020, [Multi-Domain Dialogue Acts and Response Co-Generation](https://md.research.elamur.ai/free/en/papers/wang-2020-multi-domain-dialogue-acts-response/) revisits the two-stage pipeline of task-oriented dialogue, where acts are predicted first and text is generated afterwards. It argues that acts should be modelled with the hierarchy they share across domains, and that the generator should attend to whichever act matters for each part of a reply. The newest work, [Directed Acyclic Graph Network for Conversational Emotion Recognition](https://md.research.elamur.ai/free/en/papers/shen-2021-directed-acyclic-graph-network-conversational/) (2021), assigns an emotion to every utterance in a dialogue. It combines the strengths of graph-based and recurrence-based models by representing a conversation as a directed acyclic graph through which information passes only forward in time, keeping both distant context and turn order. Quan is based at Sun Yat-sen University in Guangzhou, after earlier periods at City University of Hong Kong and the Institute for Infocomm Research in Singapore. Co-authors on more than one paper here include [Weizhou Shen](https://md.research.elamur.ai/free/en/authors/weizhou-shen/), [Rui Wang](https://md.research.elamur.ai/free/en/authors/rui-wang/), Kai Wang and Yunyi Yang. 3 papers on this site · 2020–2021 current affiliation [Sun Yat-sen University](https://md.research.elamur.ai/free/en/universities/sun-yat-sen-university/), Guangzhou, China; [Sun Yat-sen Memorial Hospital](https://ror.org/01px77p81), Guangzhou, China Xiaojun Quan has 3 papers on this site, in 2020–2021, most of them on [Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/), [Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/), [Speech act theory](https://md.research.elamur.ai/free/en/topics/speech-act-theory/); often with [Kai Wang](https://md.research.elamur.ai/free/en/authors/kai-wang/), [Rui Wang](https://md.research.elamur.ai/free/en/authors/rui-wang/), [Weizhou Shen](https://md.research.elamur.ai/free/en/authors/weizhou-shen/). [OpenAlex](https://openalex.org/A5040062188) · [ORCID](https://orcid.org/0000-0002-8385-1083) · [**h-index 29**](https://openalex.org/authors/A5040062188) · [123 works](https://openalex.org/works?filter=author.id:A5040062188) · [3 444 citations](https://openalex.org/works?filter=author.id:A5040062188&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [3 works on this site](https://md.research.elamur.ai/free/en/authors/xiaojun-quan/#papers) · [344 citations in our library](https://md.research.elamur.ai/free/en/authors/xiaojun-quan/cited-by/) · 6 more works in our library 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=Xiaojun+Quan) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Xiaojun+Quan) · [dblp](https://dblp.org/search?q=Xiaojun+Quan) · [ACL Anthology](https://aclanthology.org/search/?q=Xiaojun+Quan) ## Affiliations - [Sun Yat-sen University](https://md.research.elamur.ai/free/en/universities/sun-yat-sen-university/) · Guangzhou, China —current · 2017–2033 on 95 papers · employment 2017–2033 (Wikidata) - [Sun Yat-sen Memorial Hospital](https://ror.org/01px77p81) · Guangzhou, China —current · 2026 on 1 paper - [Institute for Infocomm Research](https://md.research.elamur.ai/free/en/labs/institute-for-infocomm-research/) · Singapore, Singapore —2014–2017 on 5 papers · employment 2014–2017 (Wikidata) - [City University of Hong Kong](https://md.research.elamur.ai/free/en/universities/city-university-of-hong-kong/) · Hong Kong, Hong Kong —2009–2015 on 22 papers · education 2009–2012 (Wikidata) · employment 2012–2013 (Wikidata) - [Agency for Science, Technology and Research](https://md.research.elamur.ai/free/en/government/agency-for-science-technology-and-research/) · Singapore, Singapore —2014–2015 on 3 papers - [University of Science and Technology of China](https://md.research.elamur.ai/free/en/universities/university-of-science-and-technology-of-china/) · Hefei, China —2008–2009 on 2 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 more institutions on single bylines are not listed. ## Topics [Sentiment & emotion 2](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · [Dialogue systems 2](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · [Speech act theory 1](https://md.research.elamur.ai/free/en/topics/speech-act-theory/) ## Works by year ### 2020s [**2021** 1 paper](https://md.research.elamur.ai/free/en/papers/shen-2021-directed-acyclic-graph-network-conversational/) · [**2020** 2 papers](https://md.research.elamur.ai/free/en/authors/xiaojun-quan/year/2020/) ## Papers The most cited first (OpenAlex and our library). 1. **[Relational Graph Attention Network for Aspect-based Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/wang-2020-relational-graph-attention-network-aspect/)** *(2020 · 775 citations)* Aspect-based sentiment analysis (ABSA) assigns a sentiment polarity to each aspect mentioned in a review. This is difficult when one sentence contains several aspects with opposing opinions, because attention-based models often link an aspect to the wrong opinion word. The authors argue that explicit syntax focused… 2. **[Directed Acyclic Graph Network for Conversational Emotion Recognition](https://md.research.elamur.ai/free/en/papers/shen-2021-directed-acyclic-graph-network-conversational/)** *(2021 · 344 citations)* The paper tackles emotion recognition in conversation (ERC), where each utterance in a dialogue gets an emotion label. 3. **[Multi-Domain Dialogue Acts and Response Co-Generation](https://md.research.elamur.ai/free/en/papers/wang-2020-multi-domain-dialogue-acts-response/)** *(2020 · 65 citations)* Task-oriented dialogue systems usually produce a reply in two steps. They first predict dialogue acts (domain-action-slot triples) and then generate text conditioned on those acts. The authors identify two weaknesses in this pipeline. Classifying each act separately ignores the hierarchical structure that acts share… ## Also in our library 6 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. - [Kai Wang](https://md.research.elamur.ai/free/en/authors/kai-wang/) ×2 - [Rui Wang](https://md.research.elamur.ai/free/en/authors/rui-wang/) ×2 - [Weizhou Shen](https://md.research.elamur.ai/free/en/authors/weizhou-shen/) ×2 - [Yunyi Yang](https://md.research.elamur.ai/free/en/authors/yunyi-yang/) ×2 ## Cited by Papers of our library cite their works 344 times (of the 140 884 papers whose bibliographies we read); [4 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/xiaojun-quan/cited-by/).