Joachim Daiber
About me
I am an applied scientist focused on natural language processing and machine learning. I recently started something new at Kailua Labs. Previously, I was a Staff Machine Learning Engineer at Apple in California.
I received my PhD at the University of Amsterdam, where I worked with Prof. Khalil Sima’an on machine translation. From 2011 until 2013, I was a Master’s student in the EM LCT programme in Computational Linguistics at Charles University in Prague and the University of Groningen. In my Master thesis, I worked on robust dependency parsing of noisy content with Gertjan van Noord and Dan Zeman. During my undergraduate studies at Freie Universität Berlin, I worked at the German Research Center for Artifical Intelligence.
See my full CV here or connect at GitHub, LinkedIn, Facebook or write an email to daiber.joachim [at] gmail.com.
Research Interests
Within the area of Natural Language Processing, my research interests are in Machine Translation, Entity Linking and Dependency Parsing.
Software and data
- Semantic analogy-based compound splitter: An unsupervised compound splitter based on the regularities in the vector space of word embeddings.
- The Denoised Web Treebank: Dependency treebank for evaluation of parser robustness.
- FilmTit: Translation memory application for movie subtitles.
- DBpedia Spotlight: I created an efficient and more accurate version of the multilingual entity linking system DBpedia Spotlight.
- Raw Spotlight data: Raw counts for entity linking in many languages.
Blog Posts
- 15 Jan 2018 ~ Photos: 2017 in Photos
- 04 Jan 2017 ~ Books: 2016 in Books
- 12 Jan 2015 ~ Travel: Vietnam 2014
- 22 Nov 2014 ~ Poem: Ithaka by Constantine P. Cavafy
- 21 Nov 2014 ~ Poem: Still I Rise by Maya Angelou