--- title: "Jingbo Zhu — author profile and papers" description: "Jingbo Zhu, Kunming University of Science and Technology: 2 papers on Elamur Research (2013–2019), h-index 23 — affiliations, topics, co-authors and who…" canonical: "https://research.elamur.ai/free/en/authors/jingbo-zhu/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/jingbo-zhu/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Jingbo Zhu # Jingbo Zhu Jingbo Zhu works in natural language processing, and the papers here cover two areas: syntactic parsing and [machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/). Both lines of work ask how to make a model's training and search behave well. In parsing the issue is how beam search compares partial analyses. In translation it is how gradients travel through very deep networks. The methods range from transition-based parsers with global perceptron training to Transformer architectures, and the work appears here between 2013 and 2019. The most cited paper here is [Learning Deep Transformer Models for Machine Translation](https://md.research.elamur.ai/free/en/papers/wang-2019-learning-deep-transformer-models-machine/) (2019). It shows that translation encoders with many stacked layers can be trained stably. One change places layer normalization ahead of each sub-layer rather than after the residual sum, which a gradient analysis links to better error flow toward lower layers. The other is DLCL, a learned combination of earlier layers modelled on multi-step ODE solvers. The earlier [Fast and Accurate Shift-Reduce Constituent Parsing](https://md.research.elamur.ai/free/en/papers/zhu-2013-fast-accurate-shift-reduce-constituent/) (2013) asks why shift-reduce constituent parsers lagged behind chart-based ones. It traces much of the gap to unary nodes, which leave competing trees with different numbers of actions. A no-op padding action makes their scores comparable. The parser also gains features drawn from unlabeled text, among them Brown clusters, automatically parsed lexical dependencies and a dependency language model. Across the papers here, the direction moves from [syntax and grammar formalisms](https://md.research.elamur.ai/free/en/topics/syntax-grammar/) toward neural translation, where the newest work studies depth rather than width as a route to quality. Zhu's bylines point mainly to [Northeastern University](https://md.research.elamur.ai/free/en/universities/northeastern-university/) in Shenyang, China, from 2004 onward. Co-authors on the site include [Bei Li](https://md.research.elamur.ai/free/en/authors/bei-li/), [Derek F. Wong](https://md.research.elamur.ai/free/en/authors/derek-f-wong/), [Lidia S. Chao](https://md.research.elamur.ai/free/en/authors/lidia-s-chao/), [Wenliang Chen](https://md.research.elamur.ai/free/en/authors/wenliang-chen/), Min Zhang and Yue Zhang. Jingbo Zhu has 2 papers in our library, in 2013–2019, most of them on [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/), [Syntax & grammar formalisms](https://md.research.elamur.ai/free/en/topics/syntax-grammar/); often with [Bei Li](https://md.research.elamur.ai/free/en/authors/bei-li/), [Derek F. Wong](https://md.research.elamur.ai/free/en/authors/derek-f-wong/), [Lidia S. Chao](https://md.research.elamur.ai/free/en/authors/lidia-s-chao/). 2 papers in our library · 2013–2019 current affiliation [Kunming University of Science and Technology](https://ror.org/00xyeez13), Kunming, China; [Northeastern University](https://md.research.elamur.ai/free/en/universities/northeastern-university/), Boston, United States; [Northeastern University](https://md.research.elamur.ai/free/en/universities/northeastern-university-cn/), Shenyang, China [OpenAlex](https://openalex.org/A5100370155) · [ORCID](https://orcid.org/0000-0002-6537-7007) · [**h-index 23**](https://openalex.org/authors/A5100370155) · [187 works](https://openalex.org/works?filter=author.id:A5100370155) · [1 999 citations](https://openalex.org/works?filter=author.id:A5100370155&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works in our library](https://md.research.elamur.ai/free/en/authors/jingbo-zhu/#papers) · [271 citations in our library](https://md.research.elamur.ai/free/en/authors/jingbo-zhu/cited-by/) · 11 more works in our library · [⭐ Paper Star rank #1924](https://md.research.elamur.ai/free/en/paper-stars/page/20/#star-1924) 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=Jingbo+Zhu) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Jingbo+Zhu) · [dblp](https://dblp.org/search?q=Jingbo+Zhu) · [ACL Anthology](https://aclanthology.org/search/?q=Jingbo+Zhu) ## Affiliations [🎓**Northeastern University** Shenyang · China 2004–2026 · 131 papers*current*](https://md.research.elamur.ai/free/en/universities/northeastern-university-cn/) · [🎓**Northeastern University** Boston · United States 2005–2026 · 31 papers*current*](https://md.research.elamur.ai/free/en/universities/northeastern-university/) · [🎓**Kunming University of Science and Technology** Kunming · China 2026 · 1 paper*current*](https://ror.org/00xyeez13) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 6 more institutions on single bylines are not listed. ## Topics [Machine translation 1](https://md.research.elamur.ai/free/en/topics/machine-translation/) · [Syntax & grammar formalisms 1](https://md.research.elamur.ai/free/en/topics/syntax-grammar/) ## Works by year ### 2010s [**2019** 1 paper](https://md.research.elamur.ai/free/en/papers/wang-2019-learning-deep-transformer-models-machine/) · [**2013** 1 paper](https://md.research.elamur.ai/free/en/papers/zhu-2013-fast-accurate-shift-reduce-constituent/) ## Papers The most cited first (OpenAlex and our library). 1. **[Learning Deep Transformer Models for Machine Translation](https://md.research.elamur.ai/free/en/papers/wang-2019-learning-deep-transformer-models-machine/)** *(2019 · 798 citations)* Transformer systems for machine translation have usually gained quality by becoming wider (Transformer-Big). 2. **[Fast and Accurate Shift-Reduce Constituent Parsing](https://md.research.elamur.ai/free/en/papers/zhu-2013-fast-accurate-shift-reduce-constituent/)** *(2013 · 247 citations)* Transition-based dependency parsers with beam search and global training already match chart-based parsers, but shift-reduce constituent parsers have trailed the state-of-the-art. ## Also in our library 11 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 6 co-authors with a page, the most papers together first. - [Bei Li](https://md.research.elamur.ai/free/en/authors/bei-li/) - [Derek F. Wong](https://md.research.elamur.ai/free/en/authors/derek-f-wong/) - [Lidia S. Chao](https://md.research.elamur.ai/free/en/authors/lidia-s-chao/) - [Min Zhang](https://md.research.elamur.ai/free/en/authors/min-zhang/) - [Wenliang Chen](https://md.research.elamur.ai/free/en/authors/wenliang-chen/) - [Yue Zhang](https://md.research.elamur.ai/free/en/authors/yue-zhang/) ## Cited by Papers of our library cite their works 271 times (of the 140 884 papers whose bibliographies we read); [15 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/jingbo-zhu/cited-by/).