Dr. Carolin Lawrence (Haas)
Machine Learning Research Scientist
NEC Labs Europe
Heidelberg, Germany
Machine Learning Research Scientist
NEC Labs Europe
Heidelberg, Germany
I am a research scientist in the Machine Learning group of NEC Labs Europe. I work on natural language processing (NLP), graph structured data and making machine-learnt models more interpretable. Together with colleagues, I have recently developed a method for bidirectional sequence generation (BiSon), which we have for example applied to improve dialogue generation for chat bots.
From 2014-2018 I was graduate research assistant and PhD student at the Statistical NLP group at the Heidelberg University, supervised by Prof. Dr. Stefan Riezler. During my PhD I worked on Natural Language Processing (NLP) problems, such as machine translation and question-answering, and I explored how reinforcement learning can be applied to these problems.
Research Interests
- Machine Learning, particularly for Graph-structured Data and using Reinforcement Learning
- Natural Language Processing, particularly Question-Answering and Dialogue
- Explainable AI: AI should enrich our lives and for this we should work on interpretable, trustworthy and inclusive AI
News
2020
- September 24: Talk at the first virtual Heidelberg Laureate Forum (HLF) about “The Knowledge Pipeline: Extract, Enrich and Explain”.
- July 14: Blog post that summarices the ACL 2020 track “Interpretability and Analysis of Models for NLP”
- July 3-10: I was an official microblogger for ACL 2020, focusing on the track “Interpretability and Analysis of Models for NLP” (see also my Twitter handle below). I’m also one of the mentors at ACL 2020.
- May 13: Talk at the StatNLP Colloquium about “Bidirectional Sequence Generation and its Prototype Transfer”.
- April 30: Talk at KMD’s STEAM talk series about how to “Extract, Enrich & Explain Knowledge”.
- February 3: New blog post about our paper “Attending to Future Tokens for Bidirectional Sequence Generation”
- January 14: Lecture on reinforcement learning and its applications to sequence-to-sequence NLP at the ECOLE winter school
- Reviewing Activities: EMNLP, ACL, IJCAI, COLING, RepL4NLP
2019
- November 5: Presented my EMNLP paper with my colleagues Bhushan Kotnis and Mathias Niepert at EMNLP as the first oral presentation of the conference. Hong Kong, China.
Code. - November 4: Presented my EMNLP paper with my colleagues Bhushan Kotnis and Mathias Niepert at the 3rd Workshop on Neural Generation and Translation (WNGT 2019). Hong Kong, China.
Code. - October 22: Talk at the colloquium of the Data and Web Science Group, University of Mannheim.
- July 29: I presented my TACL paper with my colleague Laura Jehl and PhD advisor Stefan Riezler at ACL as an oral presentation. Florence, Italy.
Code. - May 20 - 22: Presented our abstract “Building a Biomedical Knowledge Graph and Predicting Novel Relations” with my colleagues Timo Sztyler and Brandon Malone at the workshop Scientific Literature Knowledge Bases, co-located with the Automated Knowledge Base Construction (AKBC) conference, where NEC Labs Europe was a sponsor. Amherst, USA.
- May 9: I successfuylly defended my doctoral thesis with the highest distinction, summa cum lauda.
- January 1: I joined NEC Labs Europe as a Research Scientist.
- Reviewing Activities 2019: NAACL, ACL, EMNLP, LMID.