--- title: "Zhisong Zhang — author profile and papers" description: "Zhisong Zhang, Huaibei Normal University: 5 papers on Elamur Research (2016–2019), h-index 23 — affiliations, topics, co-authors and who cites them in…" canonical: "https://research.elamur.ai/free/en/authors/zhisong-zhang/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/zhisong-zhang/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Zhisong Zhang # Zhisong Zhang Zhisong Zhang works in natural language processing. The papers here centre on [discourse analysis](https://md.research.elamur.ai/free/en/topics/discourse-analysis/) and also extend into [multilingual and cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/). A recurring question is how to recognise the sense of an implicit discourse relation, the link between two adjacent text spans when no connective such as "because" marks it. The methods are neural: convolutional and recurrent encoders built over word, part-of-speech and character information. They are tested on the Penn Discourse Treebank and in the CoNLL shared task on shallow discourse parsing. The most cited paper here is [Choosing Transfer Languages for Cross-Lingual Learning](https://md.research.elamur.ai/free/en/papers/lin-2019-choosing-transfer-languages-cross-lingual/). It replaces intuition about which better-resourced language to borrow training data from with a learning-to-rank framework called LangRank. Among the discourse papers, [Adversarial Connective-exploiting Networks](https://md.research.elamur.ai/free/en/papers/qin-2017-adversarial-connective-exploiting-networks-implicit/) draws on connectives that annotators inserted into the treebank, which are available only at training time, to help classify implicit relations. [A Stacking Gated Neural Architecture](https://md.research.elamur.ai/free/en/papers/qin-2016-stacking-gated-neural-architecture-implicit/) encodes each argument with a shared CNN and combines the two vectors through a collaborative gated network inspired by Highway Networks. Related work adds character-derived vectors to ordinary word embeddings, and a CoNLL 2016 system swaps new sense classifiers into an existing discourse parsing pipeline. The newest work here, from 2019, moves from analysing relations within a single language toward transfer across languages for low-resource settings. In the LangRank paper, choosing a source language is itself something a model learns from experience rather than something fixed by language family alone. Zhang is currently at [City University of Hong Kong](https://md.research.elamur.ai/free/en/universities/city-university-of-hong-kong/). Earlier papers carry the bylines of [Shanghai Jiao Tong University](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/), where the discourse parsing work was done, and of [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/). Some more recent papers list [Tencent](https://md.research.elamur.ai/free/en/companies/tencent/) and the [Chinese University of Hong Kong](https://md.research.elamur.ai/free/en/universities/chinese-university-of-hong-kong/). The most frequent co-authors are [Lianhui Qin](https://md.research.elamur.ai/free/en/authors/lianhui-qin/) and [Hai Zhao](https://md.research.elamur.ai/free/en/authors/hai-zhao/), partners on the discourse papers. The cross-lingual paper was written with a larger group that includes Yu-Hsiang Lin and Antonios Anastasopoulos. Zhisong Zhang has 5 papers in our library, in 2016–2019, most of them on [Discourse analysis](https://md.research.elamur.ai/free/en/topics/discourse-analysis/), [Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/); often with [Hai Zhao](https://md.research.elamur.ai/free/en/authors/hai-zhao/), [Lianhui Qin](https://md.research.elamur.ai/free/en/authors/lianhui-qin/), [Antonios Anastasopoulos](https://md.research.elamur.ai/free/en/authors/antonios-anastasopoulos/). 5 papers in our library · 2016–2019 [OpenAlex](https://openalex.org/A5101677227) · [ORCID](https://orcid.org/0000-0002-3680-8701) · [Wikidata](https://www.wikidata.org/wiki/Q91378234) · [**h-index 23**](https://openalex.org/authors/A5101677227) · [68 works](https://openalex.org/works?filter=author.id:A5101677227) · [4,689 citations](https://openalex.org/works?filter=author.id:A5101677227&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 5 works in our library](https://md.research.elamur.ai/free/en/authors/zhisong-zhang/#papers) · [🔗 445 citations in our library](https://md.research.elamur.ai/free/en/authors/zhisong-zhang/cited-by/) · [8 more in our library without a page yet](#also) · [⭐ Paper Star rank #2593](https://md.research.elamur.ai/free/en/paper-stars/page/26/#star-2593) 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=Zhisong+Zhang) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Zhisong+Zhang) · [dblp](https://dblp.org/search?q=Zhisong+Zhang) · [ACL Anthology](https://aclanthology.org/search/?q=Zhisong+Zhang) ## Affiliations [🎓**Huaibei Normal University** Huaibei · China 2001–2026 · 18 papersEmployment since 2001*current*](https://ror.org/03ek23472) · [🎓**City University of Hong Kong** Hong Kong · Hong Kong 2025–2026 · 4 papers*current*](https://md.research.elamur.ai/free/en/universities/city-university-of-hong-kong/) · [🎓**Carnegie Mellon University** Pittsburgh · United States 2018–2025 · 18 papers](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) · [🏢**Tencent** Shenzhen · China 2024–2025 · 6 papers](https://md.research.elamur.ai/free/en/companies/tencent/) · [🎓**Shanghai Jiao Tong University** Shanghai · China 2015–2018 · 6 papers](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/) · [🎓**Chinese University of Hong Kong** Hong Kong · Hong Kong 2024–2025 · 3 papers](https://md.research.elamur.ai/free/en/universities/chinese-university-of-hong-kong/) · [🔬**Institute for Health Innovation & Technology** Singapore · Singapore 2019–2020 · 2 papers](https://ror.org/04zap5v53) · [🎓**National University of Singapore** Singapore · Singapore 2019–2020 · 2 papers](https://md.research.elamur.ai/free/en/universities/national-university-of-singapore/) · [🏛️**National Research Council Canada** Ottawa · Canada 2019 · 2 papers](https://md.research.elamur.ai/free/en/government/national-research-council-canada/) · [🎓**Nanjing Normal University** Nanjing · China 2004–2008Education 2004–2008](https://ror.org/036trcv74) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 more institutions on single bylines are not listed. ## Topics [Discourse analysis (4)](https://md.research.elamur.ai/free/en/topics/discourse-analysis/) · [Multilingual & cross-lingual NLP (1)](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) ## Works by year ### 2010s [**2019** 1 paper](https://md.research.elamur.ai/free/en/papers/lin-2019-choosing-transfer-languages-cross-lingual/) · [**2017** 1 paper](https://md.research.elamur.ai/free/en/papers/qin-2017-adversarial-connective-exploiting-networks-implicit/) · [**2016** 3 papers](https://md.research.elamur.ai/free/en/authors/zhisong-zhang/year/2016/) ## Papers The most cited first (OpenAlex and our library). 1. **[Choosing Transfer Languages for Cross-Lingual Learning](https://md.research.elamur.ai/free/en/papers/lin-2019-choosing-transfer-languages-cross-lingual/)** *(2019 · 313 citations)* Cross-lingual transfer helps NLP for low-resource languages by borrowing training data from a better-resourced language. 2. **[Adversarial Connective-exploiting Networks for Implicit Discourse Relation Classification](https://md.research.elamur.ai/free/en/papers/qin-2017-adversarial-connective-exploiting-networks-implicit/)** *(2017 · 144 citations)* The paper addresses implicit discourse relation classification. In this task, two adjacent arguments carry a relation (e.g., Cause) without an overt connective such as "because". The authors note that explicit relations are easy to classify (over 85% accuracy), while implicit ones stay below roughly 50%. They… 3. **[A Stacking Gated Neural Architecture for Implicit Discourse Relation Classification](https://md.research.elamur.ai/free/en/papers/qin-2016-stacking-gated-neural-architecture-implicit/)** *(2016 · 98 citations)* Implicit discourse relations hold between adjacent sentences that have no connective such as "because." They are the hardest part of discourse parsing because the sense must be inferred from the content of the two arguments alone. 4. **[Shallow Discourse Parsing Using Convolutional Neural Network](https://md.research.elamur.ai/free/en/papers/qin-2016-shallow-discourse-parsing-convolutional-neural/)** *(2016 · 47 citations)* This system was built by the Shanghai Jiao Tong University team for the CoNLL 2016 Shared Task on shallow discourse parsing in English and Chinese. 5. **[Implicit Discourse Relation Recognition with Context-aware Character-enhanced Embeddings](https://md.research.elamur.ai/free/en/papers/qin-2016-implicit-discourse-relation-recognition-context/)** *(2016 · 46 citations)* Implicit discourse relations are links between two text spans (Arg1, Arg2) that lack an overt connective such as "so" or "but". ## Also in our library 8 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 11 co-authors with a page, the most papers together first. - [Hai Zhao](https://md.research.elamur.ai/free/en/authors/hai-zhao/) ×4 - [Lianhui Qin](https://md.research.elamur.ai/free/en/authors/lianhui-qin/) ×4 - [Antonios Anastasopoulos](https://md.research.elamur.ai/free/en/authors/antonios-anastasopoulos/) - [Eric Xing](https://md.research.elamur.ai/free/en/authors/eric-xing/) - [Junxian He](https://md.research.elamur.ai/free/en/authors/junxian-he/) - [Mengzhou Xia](https://md.research.elamur.ai/free/en/authors/mengzhou-xia/) - [Patrick Littell](https://md.research.elamur.ai/free/en/authors/patrick-littell/) - [Shruti Rijhwani](https://md.research.elamur.ai/free/en/authors/shruti-rijhwani/) - [Xuezhe Ma](https://md.research.elamur.ai/free/en/authors/xuezhe-ma/) - [Yu-Hsiang Lin](https://md.research.elamur.ai/free/en/authors/yu-hsiang-lin/) - [Zhiting Hu](https://md.research.elamur.ai/free/en/authors/zhiting-hu/) ## Cited by Papers of our library cite their works 445 times (of the 140,884 papers whose bibliographies we read); [62 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/zhisong-zhang/cited-by/).