--- title: "Erik Tjong Kim Sang — author profile and papers" description: "Erik Tjong Kim Sang, Netherlands eScience Center: 3 papers on Elamur Research (1999–2003), h-index 12 — affiliations, topics, co-authors and who cites…" canonical: "https://research.elamur.ai/free/en/authors/erik-tjong-kim-sang/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/erik-tjong-kim-sang/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Erik Tjong Kim Sang # Erik Tjong Kim Sang Erik Tjong Kim Sang works on text chunking, the task of dividing a sentence into short, non-overlapping groups of words that form syntactic units, such as noun phrases, verb phrases or prepositional phrases. The papers here, from 1999 and 2000, treat chunking as a machine learning problem in which every word receives a tag. They ask how decisions made in setting up the task affect how hard it is to learn. These decisions include how chunks are encoded as tags, how training material is produced and what inputs the learner receives. The material is English newspaper text from the Wall Street Journal part of the Penn Treebank. The most cited paper here is [Representing Text Chunks](https://md.research.elamur.ai/free/en/papers/sang-1999-representing-text-chunks/) (1999). It builds on Ramshaw and Marcus (1995), who recast base noun phrase chunking as tagging, and it compares seven ways of encoding that task as tags. It also tests ways of structuring the learner. In one design, separate partial taggers predict where chunks begin, where they end and which words fall inside or outside them, and their outputs are then merged. Another design is a two-stage cascade. Its second stage leaves out the first stage's guess for the word in focus, because that guess is correct so often that it would swamp the other features. That stage also combines first-stage runs that use different context widths. The newer paper, [Introduction to the CoNLL-2000 Shared Task Chunking](https://md.research.elamur.ai/free/en/papers/sang-2000-introduction-conll-2000-shared-task/) (2000), extends the problem from base noun phrases to eleven chunk types. No corpus had been labelled by hand for such chunks, so a script generated the annotation from existing parse trees. Under its head-based rule, a chunk ends at its syntactic head and keeps premodifiers but excludes arguments and postmodifiers. The configurable converter was released alongside the data so that others could vary these decisions. Inputs carried tags from a standard part-of-speech tagger rather than the treebank's own tags. Tjong Kim Sang is currently at the Netherlands eScience Center in Amsterdam. Earlier bylines list the Meertens Institute, the [University of Amsterdam](https://md.research.elamur.ai/free/en/universities/university-of-amsterdam/), the [University of Groningen](https://md.research.elamur.ai/free/en/universities/university-of-groningen/) and the [University of Antwerp](https://md.research.elamur.ai/free/en/universities/university-of-antwerp/). One paper here was written with [Sabine Buchholz](https://md.research.elamur.ai/free/en/authors/sabine-buchholz/). Erik Tjong Kim Sang has 3 papers in our library, in 1999–2003, most of them on [Named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/); often with [Sabine Buchholz](https://md.research.elamur.ai/free/en/authors/sabine-buchholz/). 3 papers in our library · 1999–2003 [OpenAlex](https://openalex.org/A5086528773) · [ORCID](https://orcid.org/0000-0002-8431-081X) · [**h-index 12**](https://openalex.org/authors/A5086528773) · [59 works](https://openalex.org/works?filter=author.id:A5086528773) · [742 citations](https://openalex.org/works?filter=author.id:A5086528773&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 3 works in our library](https://md.research.elamur.ai/free/en/authors/erik-tjong-kim-sang/#papers) · [🔗 1,916 citations in our library](https://md.research.elamur.ai/free/en/authors/erik-tjong-kim-sang/cited-by/) · [6 more in our library without a page yet](#also) · [⭐ Paper Star rank #1052](https://md.research.elamur.ai/free/en/paper-stars/page/11/#star-1052) 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=Erik+Tjong+Kim+Sang) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Erik+Tjong+Kim+Sang) · [dblp](https://dblp.org/search?q=Erik+Tjong+Kim+Sang) · [ACL Anthology](https://aclanthology.org/search/?q=Erik+Tjong+Kim+Sang) ## Affiliations [🤝**Netherlands eScience Center** Amsterdam · Netherlands 2017–2026 · 38 papers*current*](https://ror.org/00rbjv475) · [🎓**University of Antwerp** Antwerp · Belgium 1999–2003 · 14 papers](https://md.research.elamur.ai/free/en/universities/university-of-antwerp/) · [🔬**Meertens Institute** Amsterdam · Netherlands 2013–2017 · 13 papers](https://ror.org/05kaxyq51) · [🎓**University of Amsterdam** Amsterdam · Netherlands 2005–2009 · 10 papers](https://md.research.elamur.ai/free/en/universities/university-of-amsterdam/) · [🎓**University of Groningen** Groningen · Netherlands 2001–2012 · 9 papers](https://md.research.elamur.ai/free/en/universities/university-of-groningen/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed. ## Topics [Named entity recognition (1)](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/) ## Works by year ### 2000s [**2003** 1 paper](https://md.research.elamur.ai/free/en/papers/sang-2003-introduction-conll-2003-shared-task/) · [**2000** 1 paper](https://md.research.elamur.ai/free/en/papers/sang-2000-introduction-conll-2000-shared-task/) ### 1990s [**1999** 1 paper](https://md.research.elamur.ai/free/en/papers/sang-1999-representing-text-chunks/) ## Papers The most cited first (OpenAlex and our library). 1. **[Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition](https://md.research.elamur.ai/free/en/papers/sang-2003-introduction-conll-2003-shared-task/)** *(2003 · 1,479 citations)* The paper summarizes the CoNLL-2003 shared task on named entity recognition (NER), which was intended to be language-independent. 2. **[Representing Text Chunks](https://md.research.elamur.ai/free/en/papers/sang-1999-representing-text-chunks/)** *(1999 · 569 citations)* The paper asks whether the way noun phrase chunks are encoded as per-word tags changes how well a learner can find them. Ramshaw and Marcus (1995) had turned baseNP chunking into a tagging problem. The authors compare seven encodings of that task: 3. **[Introduction to the CoNLL-2000 Shared Task Chunking](https://md.research.elamur.ai/free/en/papers/sang-2000-introduction-conll-2000-shared-task/)** *(2000 · 276 citations)* The paper presents the CoNLL-2000 shared task on text chunking, which means splitting sentences into non-overlapping, syntactically coherent word groups such as noun, verb and prepositional phrases. ## 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 1 co-author with a page, the most papers together first. - [Sabine Buchholz](https://md.research.elamur.ai/free/en/authors/sabine-buchholz/) ## Cited by Papers of our library cite their works 1,916 times (of the 140,884 papers whose bibliographies we read); [135 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/erik-tjong-kim-sang/cited-by/).