profile icon
Dr

Lea Frermann

Lecturer
question answering
language acquisition
summarization
categorization
common sense modeling
NLP on long texts
meaning change
large set
psychology
Lea Frermann's Profile Picture
Dr

Lea Frermann

 
Division
Engineering
 
Primary Interest
Computational Cognitive Modeling
Lea Frermann's Profile Picture
Dr

Lea Frermann

 

Lea Frermann is a Lecturer in the School of Computing and Information Systems, in the field of natural language processing (NLP). Her research interests focus on improving automatic understanding of long and complex texts (books, movie scripts), with help of access to common sense knowledge.

She is also interested in using machine learning for a deeper understanding of human language processing, and in using such insights to improve automatic language understanding.

Prior to joining Melbourne University, Lea obtained a PhD from the University of Edinburgh. She was a postdoc at both University of Edinburgh and Amazon Research (Berlin), and spent research visits to a variety of institutions, including Stanford University and Columbia University (New York).

Projects

Displaying the most recent project by Lea Frermann.

Project icon

Fairness In Natural Language Processing

2020 - 2023
Active

1

Projects

Project Types

1

Research Grant

Scholarly Works

Displaying the 9 most recent scholarly works by Lea Frermann.

Scholarly works icon

Whodunnit? Crime Drama as a Case for Natural Language Understanding

Lea Frermann, Shay B Cohen, Mirella Lapata

Journal article  |  2018  |  Transactions of the Association for Computational Linguistics

In this paper we argue that crime drama exemplified in television programs such as CSI: Crime Scene Investigation is an ideal test..

Scholarly works icon

Unsupervised Induction of Linguistic Categories with Records of Reading, Speaking, and Writing

Maria Barrett, Ana Valeria Gonzalez-Garduño, Lea Frermann, Anders Søgaard

Conference Proceedings  |  2018  |  Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

When learning POS taggers and syntactic chunkers for low-resource languages, different resources may be available, and often all w..

Scholarly works icon

Inducing Semantic Micro-Clusters from Deep Multi-View Representations of Novels

Lea Frermann, György Szarvas

Conference Proceedings  |  2017  |  Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Automatically understanding the plot of novels is important both for informing literary scholarship and applications such as summa..

Scholarly works icon

A Bayesian Model of Diachronic Meaning Change

Lea Frermann, Mirella Lapata

Journal article  |  2016  |  Transactions of the Association for Computational Linguistics

Word meanings change over time and an automated procedure for extracting this information from text would be useful for historical..

Scholarly works icon

Incremental Bayesian Category Learning From Natural Language

Lea Frermann, Mirella Lapata

Journal article  |  2016  |  Cognitive Science

Scholarly works icon

A Bayesian model for joint learning of categories and their features

L Frermann, M Lapata

Conference Proceedings  |  2015  |  Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

© 2015 Association for Computational Linguistics. Categories such as ANIMAL or FURNITURE are acquired at an early age and play an ..

Scholarly works icon

Incremental Bayesian learning of semantic categories

L Frermann, M Lapata

Conference Proceedings  |  2014  |  Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics

Models of category learning have been extensively studied in cognitive science and primarily tested on perceptual abstractions or ..

Scholarly works icon

A hierarchical Bayesian model for unsupervised induction of script knowledge

L Frermann, I Titov, M Pinkal

Conference Proceedings  |  2014  |  Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics

Scripts representing common sense knowledge about stereotyped sequences of events have been shown to be a valuable resource for NL..

Scholarly works icon

Cross-lingual parse disambiguation based on semantic correspondence

L Frermann, F Bond

Conference Proceedings  |  2012  |  50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference

We present a system for cross-lingual parse disambiguation, exploiting the assumption that the meaning of a sentence remains uncha..

9

Scholarly Works

Keyword Analysis

Expanding Knowledge
Artificial Intelligence and Image Processing
Cognitive Sciences

Credentials

Positions

Lecturer

Computing And Information Systems

Education

Doctor of Philosophy

The University of Edinburgh

Master of Science

Universitaet des Saarlandes

Bachelor of Arts

Universitaet Bremen

Links