|
Dr Julie WeedsSenior Lecturer in Data Science, FHEADepartment of Informatics University of Sussex Brighton BN1 9QH, UK
|
|
|
Dr Julie WeedsSenior Lecturer in Data Science, FHEADepartment of Informatics University of Sussex Brighton BN1 9QH, UK
|
* MA Computer Science (1st class) Trinity Hall, Cambridge University 1995 - 1998.
* MPhil Computer Speech and Language Processing, Cambridge University 1999-2000
* DPhil Natural Language Processing, University of Sussex, under the supervision of David Weir 2000 - 2003.
* Secondary Mathematics teacher, 2005 - 2011
* Postdoctoral Research Fellow, University of Sussex, 2003 - 2005 and 2012 - 2016 (PT)
* Senior Lecturer, University of Sussex, 2016 -
* Fellow of the Higher Education Academy, 2017 -
My research interests lie generally in the field of Statistical Natural Language Processing and machine learning. My doctorate was on measures and applications of lexical distributional similarity. From 2003 to 2005 I worked on the use of ontologies in the area of natural language service composition. Between 2012 and 2015, I worked on DisCo, a joint research project, investigating formal and distributional models of compositional semantics, between the universities of Cambridge, Edinburgh, Oxford, Sussex and York. From 2015 to 2016 I was a part-time research fellow in the Sussex Humanities Lab, a new research centre for the digital humanities. I am now a lecturer in Data Science and long-standing member of the TAG lab. My specific interests are the evaluation of models for composing vector representations of meaning, distinguishing different semantic relations automatically and linguistic variation. I am also interested in the application of natural language processing and machine learning techniques to large datasets to discover meaningful insights.
I am always interested in talking to high calibre students who potentially wish to undertake a PhD in the area of Natural Language Processing.
Towards Structure-Aware Paraphrase Identification with Phrase Alignment Using Sentence Encoders Qiwei Peng, David Weir and Julie Weeds. In Proceedings of COLING 2022 Gyeongju, Republic of Korea, October 2022
Testing Large Language Models on Compositionality and Inference with Phrase-Level Adjective-Noun Entailment Lorenzo Bertolini, Julie Weeds and David Weir. In Proceedings of COLING 2022 Gyeongju, Republic of Korea, October 2022
MuSeCLIR: A Multiple Senses and Cross-Lingual Information Retrieval Dataset Wing Yan Li, Julie Weeds and David Weir. In Proceedings of COLING 2022 Gyeongju, Republic of Korea, October 2022
Cognitive Sociolinguistic Variation in the Old Bailey Voices Corpus: The Case for a New Concept-Led Framework Justyna Robinson and Julie Weeds. In Transactions of the Philological Society 120(3): 399 - 426, December 2022
Structure-aware Sentence Encoder in Bert-Based Siamese Network Qiwei Peng, David Weir and Julie Weeds. In Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP) August 2021
Data augmentation for hypernymy detection Thomas Kober, Julie Weeds, Lorenzo Bertolini and David Weir. In Proceedings of the 16th Conference of the European Chapter of the Association for Association for Computational Linguistics (EACL). Online, April 2021
Improving Mental Health using Machine Learning to Assist Humans in the the Moderation of Forum Posts Dong Wang, Julie Weeds and Ian Comley. In Proceedings of Health Informatics 2020 Valletta, Malta, February 2020
Data Mining in Clinical Trial Text: Transformers for Classification and Question Answering Tasks Lena Schmidt, Julie Weeds and Julian P.T. Higgins. In Proceedings of Health Informatics 2020 Valletta, Malta, February 2020
When a Red Herring is Not a Red Herring: Using Compositional Methods to Detect Non-Compositional Phrases Julie Weeds, Thomas Kober, Jeremy Reffin and David Weir. In Proceedings of the European Chapter of the ACL (EACL-2017), Valencia, April 2017
One Representation per Word - Does it Make Sense for Composition Thomas Kober, Julie Weeds, John Wilkie, Jeremy Reffin and David Weir. In Proceedings of EACL Workshop on Sense, Concept and Entity Representations and their Applications, Valencia, April 2017
Improving Sparse Word Representations with Distributional Inference for Semantic Composition Thomas Kober, Julie Weeds, Jeremy Reffin and David Weir. In Proceedings of the International Conference on Empirical Methods for Natural Language Processing (EMNLP 2016). November 2016
A Critique of Word Similarity as a Method for Evaluating Distributional Semantic Models Miroslav Batchkarov, Thomas Kober, Jeremy Reffin, Julie Weeds and David Weir. In Proceedings of the 1st Workshop on Evaluating Vector Space Representations for NLP (ACL 2016) August 2016
Distributional Composition using Higher-Order Dependency Vectors Julie Weeds, David Weir and Jeremy Reffin. In Proceedings of the 2nd Workshop on Continuous Vector Space Models and their Compositionality (EACL 2014) April 2014.
Using Distributional Similarity to Organise Biomedical Terminology. Julie Weeds, James Dowdall, Gerold Schneider, Bill Keller and David Weir. In Special Issue of Terminology on Application-Driven Terminology Engineering Issue 11-1 June 2005.
The Distributional Similarity of Sub-parses. Julie Weeds, David Weir and Bill Keller. In Proceedings of the ACL2005 Workshop on Textual Entailment. Ann Arbor. June 2005.
Middleware for User-Controlled Environments. Bill Keller, Tim Owen, Ian Wakeman, Julie Weeds and David Weir. In Proceedings of the PerWare Workshop, PerCom 2005. Hawaii. March 2005
Managing the Policies of Non-Technical Users in a Dynamic World. Tim Owen, Ian Wakeman, Bill Keller, Julie Weeds and David Weir. In IEEE Workshop on Policy for Distributed Systems and Networks (Policy 2005)
User Policies in Pervasive Computing Environments. Jon Rimmer, Tim Owen, Ian Wakeman, Bill Keller, Julie Weeds and David Weir. In Proceedings of the Pervasive 2005 workshop on User Experience Design for Pervasive Computing. 2005
Automatic Identification of Infrequent Word Senses. Diana McCarthy, Rob Koeling, Julie Weeds and John Carroll. In Proceedings of the 20th International Conference of Computational Linguistics, COLING-2004. Geneva, Switzerland. August 2004
Finding Predominant Senses in Untagged Text. Diana McCarthy, Rob Koeling, Julie Weeds and John Carroll. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics. Barcelona, Spain. July 2004. ACL best paper award
Using Automatically Acquired Predominant Senses for Word Sense Disambiguation Diana McCarthy, Rob Koeling, Julie Weeds and John Carroll. In Proceedings of the ACL Senseval-3 Workshop. Barcelona, Spain. July 2004.
Natural Language Expression of User Policies in Pervasive Computing Environments Julie Weeds, Bill Keller, David Weir, Ian Wakeman, Jon Rimmer and Tim Owen. In Proceedings of OntoLex 2004 (LREC Workshop on Ontologies and Lexical Resources in Distributed Environments). Lisbon, Portugal. May 2004
Measures and Applications of Lexical Distributional Similarity Julie Weeds. Unpublished doctoral thesis. University of Sussex. 2003
A General Framework for Distributional Similarity Julie Weeds and David Weir. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2003). Sapporo, Japan. July 2003
Finding and Evaluating Sets of Nearest Neighbours. (pdf) Julie Weeds and David Weir. In Proceedings of the 2nd Conference of Corpus Linguistics. Lancaster. March 2003
Smoothing Using Nearest Neighbours. Julie Weeds. In Proceedings of the Sixth UK Special Interest Group for Computational Linguistics (CLUK6). Edinburgh. January 2003
The Reliability of a Similarity Measure. Julie Weeds. In Proceedings of the Fifth UK Special Interest Group for Computational Linguistics (CLUK5). Leeds. January 2002
Building Semantic Hierarchies from Machine Readable Dictionaries. In Proceedings of the Fourth UK Special Interest Group for Computational Linguistics UK (CLUK4) Sheffield. January 2001
Word Sense Disambiguation Using CIDE+Julie Weeds. Unpublished MPhil Thesis. Cambridge University. 2000 (this is about semi-automatically extracting a semantic hierarchy of noun senses from a machine readable dictionary).