Jakob

Jakob Prange

Postdoctoral Fellow

in the Department of Chinese and Bilingual Studies
at Hong Kong Polytechnic University

Email:

Affiliations | Papers | Presentations

My primary interest is to explore how human language works and how this can be formalized well and efficiently. I try to accomplish this by combining methods and concepts from formal and distributional semantics, meaning & knowledge representation, deep learning, and old-school AI. Within the fields of computational linguistics (CL) and natural language processing (NLP), I thus consider myself on the somewhat more abstract and theoretical side of the spectrum—but I'm hoping that my foundational research can at some point be applied to something that's useful in the real world (see, e.g., section 5 of our KI article for some hypothetical applications of case and adposition supersense classification).

I received a Ph.D. in Computer Science with a concentration in Cognitive Science from Georgetown University, specializing in computational syntax & semantics, meaning representation design, and parsing. My advisor was Dr. Nathan Schneider. My dissertation (titled "Neuro-symbolic Models for Constructing, Comparing, and Combining Syntactic and Semantic Representations") mostly consists of three published papers, which you can find here: abstract, chapter 3, chapter 4, chapter 5. There is a good chance I'm going to put the whole thing online soon, but feel free to reach out if you can't wait (or read it on Proquest if you have access). I am extremely grateful for the guidance I have received from my thesis committee, consisting of Nathan, Dr. Chris Dyer, Dr. Katrin Erk, Dr. Ophir Frieder, and Dr. Justin Thaler.

Before that, I got a B.S. in Computational Linguistics from Saarland University under the supervision of Prof. Dr. Manfred Pinkal and Dr. Stefan Thater. My thesis project was on "POS-Tagging of Internet Texts Using Information about Distributional Similarity" and is summarized in this paper.

ACL Anthology | GitHub | Google Scholar | Semantic Scholar | DBLP | ResearchGate | LinkedIn


Groups and projects



Tutorial

Papers


Presentations

  • Supertagging the Long Tail with Tree-Structured Decoding of Complex Categories.
    EACL, April 2021; SCiL, February 2021 (as CCG Supertagging as Top-down Tree Generation).
    [abstract], [publisher], [full paper]

  • Cross-linguistic Multilayer Semantic Annotation and Parsing with UCCA.
    U of Utah NLP group, August 2019.
    [abstract]

  • Corpus Linguistics: What is it and what can it do for me?
    1st IDHN Conference, May 2019.
    [slides]

  • Preposition Supersenses in German-English Parallel Data.
    MASC-SLL 2018; Google Assistant and Dialog Workshop 2018.
    [abstract], [poster]

  • The UdS POS Tagging Systems @ EmpiriST 2015.
    Roundtable discussion, NLP4CMC 2016.
    [slides]