Jan-Christoph Klie

Jan-Christoph Klie

PhD Student Natural Language Processing

TU Darmstadt UKP

Biography

I am a PhD student on the INCEpTION project where I am working on interactive annotation for NLP. Currently I research how several annotation tasks, e.g. creating corpora with linked entities or predicate-argument structures can be supported by interactive machine learning. In my free time, I love to learn Mandarin.

Interests
  • Interactive Machine Learning
  • Reinforcement Learning
  • Online Learning
  • Information Retrieval
  • Annotation
  • Chinese
Education

  • PhD in Computer Science, 2018 - now

    TU Darmstadt

  • MSc in Computer Science, 2017

    TU Darmstadt

  • BSc in Computer Science, 2014

    DHBW Mannheim

Recent Publications

Jan-Christoph Klie, Richard Eckart de Castilho, Iryna Gurevych (2020). From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.

PDF Cite DOI

Richard Eckart de Castilho, Nancy Ide, Jin-Dong Kim, Jan-Christoph Klie, Keith Suderman (2019). A Multi-Platform Annotation Ecosystem for Domain Adaptation. Proceedings of the 13th Linguistic Annotation Workshop.

PDF Cite DOI

Beto Boullosa, Richard Eckart de Castilho, Naveen Kumar, Jan-Christoph Klie, Iryna Gurevych (2018). Integrating Knowledge-Supported Search into the INCEpTION Annotation Platform. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations.

PDF Cite DOI

Jan-Christoph Klie, Michael Bugert, Beto Boullosa, Richard Eckart de Castilho, Iryna Gurevych (2018). The INCEpTION Platform: Machine-Assisted and Knowledge-Oriented Interactive Annotation. Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations.

PDF Cite

Teresa Botschen, Iryna Gurevych, Jan-Christoph Klie, Hatem Mousselly-Sergieh, Stefan Roth (2018). Multimodal Frame Identification with Multilingual Evaluation. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers).

PDF Cite DOI

Recent Posts

Course Review: Probability - The Science of Uncertainty and Data MITx (6.431x)
After finishing Probability and Statistics by Stanford Online, I wanted to improve my knowledge of statistics further. The logical choice was to take Probability - The Science of Uncertainty and Data MITx (6.
Aug 23, 2021 6 min read
Use pretokenized text with Huggingface transformers
For seqviz and INCEpTION external recommender, I recently had the problems that I needed to use BERT for sequence tagging but needed to predict labels for my own tokens. The problem is that transformers typically use subword tokenization like WordPiece or Sentence piece.
Sep 26, 2020 3 min read
Course Review: Economics of Money and Banking
I recently got interested in economics and finance. A post on Hacker News was recommending to take Economics of Money and Banking on Coursera as an introduction. I really enjoyed the course and will give a brief review of it here.
Jul 26, 2020 4 min read
Course Review: Probability and Statistics by Stanford Online
In order to brush up my math skills, I started the Probability and Statistics by Stanford Online. I found it via the Free online machine learning curriculum by Chip Hyuen. If you do not know her, make sure to read her blog and books!
Feb 29, 2020 5 min read
Yangtao - Our entry for the 2019 International Collegiate Competition for Brain-inspired Computing
Introduction In October, I participated together with a friend in the 2019 International Collegiate Competition for Brain-inspired Computing organized by Tsinghua University. The task was to develop an AI system
Nov 5, 2019 7 min read
See all posts

Projects

anki-maobi

máobĭ (毛笔) is an Anki add-on to create cards with writing quizzes for Hanzi.

dkpro-cassis

UIMA CAS processing library written in Python.

INCEpTION

INCEpTION provides a semantic annotation platform offering intelligent annotation assistance and knowledge management.

seqviz

seqviz is a Python package to visualize sequence tagging results. It can be either be used to print to console or in Jupyter Notebooks.

setlx2py

A SetlX to Python compiler.

vrmagic-connector

ROS package to connect a VRMagic USB camera into the ROS ecosystem.

wikimapper

Mapping Wikipedia pages to Wikidata IDs and vice versa.

Yangtao

An Android app that uses Augmented Reality to learn Chinese characters.