Dr. Benjamin Roth

Akademischer Rat
Center for Information and Language Processing
Ludwig-Maximilians-Universität München (LMU Munich)
Office: Oettingenstraße 67, Room C 106
Office Hours: Tuesday, 14:00-15:00
Email: [beroth at cis dot uni-muenchen dot de]

I am an Akademischer Rat (~assistant professor) in the area of deep learning & statistical NLP at the Center for Information and Language Processing, LMU Munich. Previously, I was an interim Professor at LMU Munich assuming the duties of Prof. Hinrich Schütze, and before that a postdoc in the Information Extraction and Synthesis Lab (IESL) at the University of Massachusetts, Amherst, working with Prof. Andrew McCallum. I did my PhD at the LSV Spoken Language Systems Lab at Saarland University under supervision by Prof. Dietrich Klakow. I am grateful for the support by a Google Europe Fellowship in Natural Language Processing for my PhD research.

My research focus lies in machine learning for relation extraction and knowledge bases. Our relation extraction system RelationFactory (on GitHub, overview, analysis) was top-ranked in the TAC KBP English Slot-Filling benchmarks, and several successful knowledge-base construction systems in TAC 2014 and 2015 were based on RelationFactory. Some of my joint work with Dr. Michael Wiegand is targeted towards entity type induction and relation extraction in the food domain. My project and work experience includes internships at Google Zurich and Xerox Research Grenoble. During my studies I worked as a programmer for the MARY text-to-speech system.

  • October 11, 2018: Invited Talk on Relational information extraction at Munich NLP Meetup
  • October 8, 2018: Invited Talk on Relation extraction for non-standard agruments at Apple Siri, Cambridge/UK
  • March 5, 2018: Invited Talk on Deep Learning for NLP at the TU Munich Center for Innovation and Business Creation (UnternehmerTUM) (slides)


Current and former students
  • Eduard Saller (2018-)
MSc theses (selection):
  • Luisa Berlanda
    Domain adaptation for part-of-speech tagging using neural networks
  • Ivan Bilan (results)
    Relation extraction using deep neural networks and self-attention
  • Eduard Saller (collaboration with BMW)
    Clustering of user intents in a spoken dialogue system
  • Kevin Falkner (collaboration with BMW)
    Clustering customer feedback for trend detection
  • Stefan Schweter
    Leveraging additional data for relation extraction with neural question answering systems
  • Elena Neuburg
    Deep learning techniques for relational pattern matching
  • Jens Illig (EACL Paper)
    Unsupervised parsing for relation extraction
BSc theses (selection):
  • Simon Steinheber
    Aspektbasierte Sentiment-Analyse mit neuronalen Netzwerken
  • Ivana Daskalovska
    Automatic generation of a data set for questions and answers
  • Yiyi Chen
    Deep learning for extraction of opinion entities
  • Florian von Unold
    Predicting the compositionality of multiword expressions using word vectors and neural networks
  • Sarah Bosch
    Maschinelles Lernen für die automatische Erkennung von “Fake-News”
  • Ziad Elsayes
    Natural language generation from structured data using neural networks
  • Sofia Chavez (collaboration with Bavarian State Library)
    Automatic segmentation for search in musical score data
  • Simon Preißner
    Classification of relations in Wikipedia links
  • Karsten Schick (collaboration with Sulzer GmbH)
    Automatische Identitätsfeststellung von Incident-Tickets


B.Roth, C. Conforti, N. Pörner, S. Karn and H. Schütze.
Neural Architectures for Open-Type Relation Argument Extraction.
preprint, 2018

M. Schulder, M. Wiegand, J. Ruppenhofer and B.Roth.
Towards Bootstrapping a Polarity Shifter Lexicon using Linguistic Features.
IJCNLP 2017.

P. Verga, D. Belanger, E. Strubell, B.Roth, and A. McCallum.
Multilingual Relation Extraction using Compositional Universal Schema.
NAACL, 2016.

M. Schuhmacher, B.Roth, S. Ponzetto and L. Dietz.
Finding Relevant Relations in Relevant Documents.
ECIR 2016.

B.Roth, N. Monath, D. Belanger, E. Strubell, P. Verga, A. McCallum.
Building Knowledge Bases with Universal Schema: Cold Start and Slot-Filling Approaches.
NIST Text Analysis Conference 2015.

A. Neelakantan, B.Roth and A. McCallum.
Compositional Vector Space Models for Knowledge Base Completion.
ACL 2015.

B.Roth, E. Strubell, K. Silverstein and A. McCallum.
Minimally Supervised Event Argument Extraction using Universal Schema.
NIPS 2014 Workshop on Knowledge Extraction (AKBC).

A. Neelakantan, B.Roth and A. McCallum.
Knowledge Base Completion using Compositional Vector Space Models.
NIPS 2014 Workshop on Knowledge Extraction (AKBC).

B.Roth, T. Barth, G. Chrupala, M. Gropp, D. Klakow.
RelationFactory: A Fast, Modular and Effective System for Knowledge Base Population.
EACL 2014 (software demo).

B.Roth, T. Barth, M. Wiegand, M. Singh, D. Klakow.
Effective Slot Filling Based on Shallow Distant Supervision Methods.
NIST Text Analysis Conference 2013.

B.Roth, T. Barth, M. Wiegand, D. Klakow.
A Survey of Noise Reduction Methods for Distant Supervision.
CIKM 2013 Workshop on Knowledge Extraction (AKBC).

M. Wiegand, B.Roth, D. Klakow.
Web-based Relation Extraction for the Food Domain.
NLDB 2012.

B.Roth, G. Chrupala, M. Wiegand, M. Singh, D. Klakow.
Generalizing from Freebase and Patterns using Distant Supervision for Slot Filling.
NIST Text Analysis Conference 2012.

M. Wiegand, B.Roth, D. Klakow.
Knowledge Acquisition with Natural Language Processing in the Food Domain: Potential and Challenges.
ECAI 2012 Workshop: Cooking with Computers.

M. Wiegand, B.Roth, D. Klakow.
Data-driven Knowledge Extraction for the Food Domain.

M. Wiegand, B.Roth, E. Lasarcyk, S. Köser, D. Klakow.
A Gold Standard for Relation Extraction in the Food Domain.
LREC 2012.

B.Roth, A. McCallum, M. Dymetman and N. Cancedda.
Machine Translation Using Overlapping Alignments and SampleRank.
AMTA 2010.

G. Chrupala, G. Dinu and B.Roth.
Enriched Syntax-based Meaning Representation for Answer Extraction.
SIGIR 2010 Workshop: Query Representation and Understanding.

M. Wiegand, A. Balahur, B.Roth, D. Klakow and A. Montoyo.
A Survey on the Role of Negation in Sentiment Analysis.
2010 Workshop on Negation and Speculation in NLP.