--- title: "Liheng Xu — author profile and papers" description: "Liheng Xu, China Jiliang University: 2 papers on Elamur Research (2015), h-index 32 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/liheng-xu/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/liheng-xu/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Liheng Xu # Liheng Xu Liheng Xu works in natural language processing, specifically on getting structured knowledge out of text and representing it for machines. Their papers here address two connected problems in [information extraction](https://md.research.elamur.ai/free/en/topics/information-extraction/) and [knowledge graphs](https://md.research.elamur.ai/free/en/topics/knowledge-graphs/): filling gaps in large knowledge bases by predicting missing facts, and pulling events and their participants from raw sentences. In both, hand-designed features and external parsing tools give way to vector representations and neural networks learned directly from data. The most cited of these papers is [Knowledge Graph Embedding via Dynamic Mapping Matrix](https://md.research.elamur.ai/free/en/papers/ji-2015-knowledge-graph-embedding-dynamic-mapping/) (2015). It introduces TransD, a translation-based model that represents each entity and each relation with two vectors, one for meaning and one for projection. Each entity–relation pair then gets its own mapping matrix, where earlier models made all entities of a relation share one. This captures how varied those entities can be and uses fewer parameters and less computation than TransR/CTransR. The second paper, [Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks](https://md.research.elamur.ai/free/en/papers/chen-2015-event-extraction-dynamic-multi-pooling/) (2015), handles ACE event extraction with a convolutional network. The network splits each sentence at the trigger and argument positions and pools each segment separately, which keeps local evidence that a single max-pool would lose. Embeddings of each word's distance to the target words tell the model where to focus. Triggers are detected first, and a similar network then labels the arguments. Both papers date from 2015 and share an approach: learned representations replace pipelines built on parsers and manual feature engineering. The current affiliation is China Jiliang University in Hangzhou. The work collected here is tied to the [Institute of Automation](https://md.research.elamur.ai/free/en/labs/institute-of-automation/), [Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/), in Beijing, where it was produced with [Jun Zhao](https://md.research.elamur.ai/free/en/authors/jun-zhao/) and [Kang Liu](https://md.research.elamur.ai/free/en/authors/kang-liu/) and with [Shizhu He](https://md.research.elamur.ai/free/en/authors/shizhu-he/), [Daojian Zeng](https://md.research.elamur.ai/free/en/authors/daojian-zeng/) and [Yubo Chen](https://md.research.elamur.ai/free/en/authors/yubo-chen/). Liheng Xu has 2 papers in our library, in 2015, most of them on [Information extraction](https://md.research.elamur.ai/free/en/topics/information-extraction/), [Knowledge graphs & ontologies](https://md.research.elamur.ai/free/en/topics/knowledge-graphs/); often with [Jun Zhao](https://md.research.elamur.ai/free/en/authors/jun-zhao/), [Kang Liu](https://md.research.elamur.ai/free/en/authors/kang-liu/), [Daojian Zeng](https://md.research.elamur.ai/free/en/authors/daojian-zeng/). 2 papers in our library · 2015 [OpenAlex](https://openalex.org/A5101422057) · [ORCID](https://orcid.org/0000-0003-4110-1548) · [**h-index 32**](https://openalex.org/authors/A5101422057) · [78 works](https://openalex.org/works?filter=author.id:A5101422057) · [7,319 citations](https://openalex.org/works?filter=author.id:A5101422057&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/liheng-xu/#papers) · [🔗 384 citations in our library](https://md.research.elamur.ai/free/en/authors/liheng-xu/cited-by/) · [⭐ Paper Star rank #829](https://md.research.elamur.ai/free/en/paper-stars/page/9/#star-829) 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=Liheng+Xu) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Liheng+Xu) · [dblp](https://dblp.org/search?q=Liheng+Xu) · [ACL Anthology](https://aclanthology.org/search/?q=Liheng+Xu) ## Affiliations [🎓**China Jiliang University** Hangzhou · China 2007–2026 · 38 papers*current*](https://ror.org/05v1y0t93) · [🏛️**Chinese Academy of Sciences** Beijing · China 2012–2015 · 9 papers](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) · [🔬**Institute of Automation** Beijing · China 2013–2015 · 8 papers](https://md.research.elamur.ai/free/en/labs/institute-of-automation/) · [🎓**Xi'an Jiaotong University** Xi'an · China 2020–2025 · 5 papers](https://md.research.elamur.ai/free/en/universities/xi-an-jiaotong-university/) · [🏢**Daqing Oilfield of CNPC** Daqing 2013–2020 · 4 papers](https://ror.org/03shhrx95) · [🎓**Henan University** Kaifeng · China 2020 · 3 papers](https://ror.org/003xyzq10) · [🎓**Zhejiang University** Hangzhou · China 2007–2020 · 3 papers](https://md.research.elamur.ai/free/en/universities/zhejiang-university/) · [🔬**Anhui Special Equipment Inspection Institute** Hefei · China 2022–2024 · 2 papers](https://ror.org/01nqeer97) 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 [Information extraction (1)](https://md.research.elamur.ai/free/en/topics/information-extraction/) · [Knowledge graphs & ontologies (1)](https://md.research.elamur.ai/free/en/topics/knowledge-graphs/) ## Works by year ### 2010s [**2015** 2 papers](https://md.research.elamur.ai/free/en/authors/liheng-xu/year/2015/) ## Papers The most cited first (OpenAlex and our library). 1. **[Knowledge Graph Embedding via Dynamic Mapping Matrix](https://md.research.elamur.ai/free/en/papers/ji-2015-knowledge-graph-embedding-dynamic-mapping/)** *(2015 · 1,936 citations)* Knowledge graphs such as WordNet and Freebase are far from complete, so models that predict missing triplets (h, r, t) are needed. 2. **[Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks](https://md.research.elamur.ai/free/en/papers/chen-2015-event-extraction-dynamic-multi-pooling/)** *(2015 · 1,170 citations)* The paper addresses ACE event extraction: finding trigger words, assigning their event subtypes, and attaching arguments with roles. ## Co-authors here 5 co-authors with a page, the most papers together first. - [Jun Zhao](https://md.research.elamur.ai/free/en/authors/jun-zhao/) ×2 - [Kang Liu](https://md.research.elamur.ai/free/en/authors/kang-liu/) ×2 - [Daojian Zeng](https://md.research.elamur.ai/free/en/authors/daojian-zeng/) - [Shizhu He](https://md.research.elamur.ai/free/en/authors/shizhu-he/) - [Yubo Chen](https://md.research.elamur.ai/free/en/authors/yubo-chen/) ## Cited by Papers of our library cite their works 384 times (of the 140,884 papers whose bibliographies we read); [27 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/liheng-xu/cited-by/).