Lea Frermann

Lecturer, CIS, Melbourne University

About

I am a lecturer in natural language processing at the University of Melbourne, School of Computing and Information Systems.

I use machine learning methods and computational models to gain a deeper understanding of the structure and dynamics of meaning representations both in language and in humans. I develop Bayesian models of how children learn categories and their structured featural representations in a joint and incremental process. I am also interested in the dynamics of meaning in natural language. I have developed models of word meaning change over centuries. Most recently I have used deep learning methods to model the structure and development of plots in books and films.

Before joining Melbourne University, I was a postdoc / applied scientist at Amazon Core AI in Berlin. As part of this position, I spend a five week visit at David Blei's lab at Columbia University, New York in spring 2019. Previously, I was a research associate in the Edinburgh NLP group , ILCC,, University of Edinburgh, working with Mirella Lapata and Shay Cohen. From July to September 2017 was a visiting scholar in Michael Frank's Language and Cognition Lab at Stanford University.


Contact Details
Lecturer
School of Computing and Information Systems
The University of Melbourne
Victoria 3010, Australia

Office: 3.04 Doug McDonell Building
Phon: +61 3 9035 9888
Email: lea.{my_lastname}@unimelb.edu.au



Mini Bio

2019 - Lecturer at Melbourne University
2018 - 2019 Postdoc at Amazon Core AI (Berlin)
2017 - 2018 Research associate at ILCC, University of Edinburgh (collaborators Mirella Lapata and Shay Cohen)
2017 Visiting scholar at Language and Cognition Lab, Stanford University (host Michael Frank)
2013 - 2017 PhD at ILCC, University of Edinburgh (supervisors Mirella Lapata and Charles Sutton)
2016 Machine Learning Internship with Amazon Berlin (3 months)
2010 - 2013 MSc in Language Science and Technology from Saarland University (supervisors Ivan Titov and Manfred Pinkal)
2012 Erasmus Mundus Research exchange to NTU Singapore. Research project with Francis Bond.
2007 - 2010 BA in Linguistics, University of Bremen, Germany.


Invited Talks and Presentations


01 / 2020 Monash Neuroscience of Consciousness Lab, Monash University, Melbourne, Australia.
Scaling Concept Learning and Story Understanding Through Natural Language Processing
11 / 2019 Complex Human Data Hub, Melbourne University, Melbourne, Australia.
Towards Conceptual Story Understanding
04 / 2019 Data Science Seminar, Columbia University, New York, USA.
Learning representations of long narratives for summarization and inference
04 / 2019 University of Toronto, Toronto, Canada.
Modeling Dynamics in Language, Learning and Inference
04 / 2019 Johns Hopkins University, Baltimore, USA.
Learning representations of long narratives for summarization and inference
07 / 2018 University of Melbourne, Melbourne, VIC.
From word learners to crime detectives: bridging the gap between human and machine learning
04 / 2018 University of Washington, Seattle, USA.
Title: Whodunnit? Crime Drama as a Case for Natural Language Understanding
02 / 2018 Univeristät Stuttgart, IMS, Stuttgart, Germany.
Title: Modelling the Dynamics of fine-grained Change in Word Meaning over Centuries
10 / 2017 Saarland University, Saarbruecken, Germany.
Title: Whodunnit? Crime Drama as a Case for Natural Language Understanding
10 / 2017 Alan Turing Institute, London, UK.
Title: Structured dynamic models of meaning for understanding language change and representing book plots
09 / 2017 CoAStaL Copenhagen Natural Language Processing Group, Copenhagen, Denmark.
Title: Structure and Dynamics of Meaning in Humans and in Language
08 / 2017 Stanford NLP Seminar Series, Stanford University, USA.
Title: Of Space Piracy and Secret Baby Romances: Deep Multi-View Book Representations and a Scalable Evaluation Framework
11 / 2016 Keynote talk at the Drift-a-LOD workshop (co-located with EKAW), Bologna.
Title: Modelling fine-grained Change in Word Meaning over centuries from Large Collections of Unstructured Text
12 / 2015 Heriot-Watt University, Edinburgh, Scotland, UK.
Title: Incremental Bayesian Learning of Semantic Categories and their Features
09 / 2015 Google NLP PhD Summit, Zürich.
07 / 2012 Invited Paper at the First Workshop on Multilingual Modeling (in conjunction with ACL 2012), Jeju, Korea.
Title: Cross-lingual Parse Disambiguation based on Semantic Correspondence


Papers


  • Lahari Poddar, Gyorgy Szarvas, Lea Frermann (2019) A Probabilistic Framework for Learning Domain Specific Hierarchical Word Embeddings , arXiv cs.CL 1910.07333.

  • Lea Frermann (2019) Extractive NarrativeQA with Heuristic Pre-Training , 2nd Workshop on Machine Reading for Question Answering (MRQA), Hong Kong.BibTeX Poster

  • Stefanos Angelidis, Diego Marcheggiani, Lluís Màrquez, Roi Blanco and Lea Frermann (2019) Book QA: Stories of Challenges and Opportunities , to appear in 2nd Workshop on Machine Reading for Question Answering (MRQA), Hong Kong.BibTeX

  • Nikos Papasarantopoulos, Lea Frermann, Mirella Lapata and Shay B. Cohen (2019) Partners in Crime: Multi-view Sequential Inference for Movie Understanding , to appear in EMNLP 2019, Hong Kong.

  • Lea Frermann, Alex Klementiev (2019) Inducing Document Structure for Aspect-based Summarization , In proceedings of ACL 2019, Florence, Italy.BibTeX Poster

  • Lea Frermann, Mirella Lapata (under submission) Categorization in the Wild: Generalizing Cognitive Models to Naturalistic Data across Languages

  • Maria Barrett, Lea Frermann, Ana Valeria Gonzalez-Garduño and Anders Søgaard , (2018) Unsupervised Induction of Linguistic Categories with Records of Reading, Speaking, and Writing , In Proceedings of NAACL-HLT 2018, New Orleans, Louisiana, USA.BibTeX

  • Lea Frermann, Shay B. Cohen and Mirella Lapata, (2018) Whodunnit? Crime Drama as a Case for Natural Language Understanding, Transactions of the Association for Computational Linguistics (TACL) .BibTeX  Data Slides

  • Lea Frermann and Michael C. Frank, (2017) Prosodic Features from Large Corpora of Child-Directed Speech as Predictors of the Age of Acquisition of Words, arXiv cs.CL 1709.09443.repo

  • Lea Frermann and Gyorgy Szarvas, (2017) Inducing Semantic Micro-Clusters from Deep Multi-View Representations of Novels, In Proceedings of the Conference on Empirical Methods on Natural Language Processing (EMNLP), Copenhagen, Denmark.BibTeXPoster

  • Lea Frermann, (2017) Bayesian Models of Category Acquisition and Meaning Development (Ph.D Thesis Abstract). The IEEE Intelligent Informatics Bulletin, 18, (1), 23.

  • Lea Frermann, (2017) Bayesian Models of Category Acquisition and Meaning Development , Ph.D Thesis, University of Edinburgh, Scotland, UK.

  • Lea Frermann and Mirella Lapata, (2016)A Bayesian Model of Diachronic Meaning Change , Transactions of the Association for Computational Linguistics (TACL).BibTeXSlides*Code*

  • Lea Frermann and Mirella Lapata, (2016) Incremental Bayesian Category Learning from Natural Language, Cognitive Science.BibTeX

  • Lea Frermann, (2016)A Bayesian Model of Joint Category and Feature Learning 11th Workshop for Women in Machine Learning (WiML) in conj. with NIPS, Barcelona, Spain.Poster

  • Lea Frermann and Mirella Lapata, (2015) A Bayesian Model for Joint Learning of Categories and their Features, In Proceedings of NAACL-HLT 2015, Denver, Colorado, USA.BibTeXSlides

  • Lea Frermann, (2015) A Bayesian Model of the Temporal Dynamics of Word Meaning 10th Workshop for Women in Machine Learning (WiML) in conj. with NIPS, Montreal, Canada.Poster

  • Lea Frermann and Mirella Lapata, (2014) Incremental Bayesian Learning of Semantic Categories, In Proceedings of EACL 2014, Gothenburg, Sweden.BibTeXDataPoster

  • Lea Frermann, Ivan Titov and Manfred Pinkal, (2014) A Hierarchical Bayesian Model for Unsupervised Induction of Script Knowledge , In Proceedings of EACL 2014, Gothenburg, Sweden.BibTeXSlides

  • Lea Frermann, (2013) A Hierarchical Bayesian Model for Unsupervised Learning of Script Knowledge , MSc Thesis, Saarland University, Germany.

  • Lea Frermann and Francis Bond, (2012) Cross-lingual Parse Disambiguation based on Semantic Correspondence, In Proceedings of ACL 2012, Jeju, Republic of Korea.BibTeX

  • Lea Frermann, (2010) Information Extraction from Written Natural Language Input to Interactive Wayfinding Systems BA Thesis, University of Bremen, Germany.
  • PhD and MSc Students

    Kemal Kurniawan, Ph.D. (co-supervised with Trevor Cohn)
    Chunhua Liu, Ph.D. (co-supervised with Trevor Cohn)
    Ansh Bordia, M.Sc.
    Aravind Kottor Ramalakshmi, M.Sc.

    Teaching

    2019 (semester 2) Knowledge Technologies (COMP90049)