Search

Natural language processing

What are the methods and applications of enabling computers to process and understand human language?

Status

Research areas

Aims

This interest group focuses both on core natural language processing methods and tasks (such as text classification, information extraction, summarisation) and applications of natural language processing to the social sciences and humanities.

Please visit our website for more information.

How to get involved

Click here to request sign-up and join

Organisers

Dr Maria Liakata

Professor Maria Liakata

Turing AI Fellow

Adam Tsakalidis

Adam Tsakalidis

Visiting Researcher

Anthony Hills

Mr Anthony Hills

PhD student, Queen Mary University of London

Researchers

Dr Scott Hale

Dr Scott Hale

Turing Fellow

Professor Thomas Lukasiewicz

Professor Thomas Lukasiewicz

Turing Fellow

Dr. Beatrice Alex

Dr Beatrice Alex

Chancellor's Fellow at the University of Edinburgh

Dr Annie Louis

Turing Research Fellow

Foto of Barbara McGillivray

Dr Barbara McGillivray

Turing Fellow

Elena Kochkina

Dr Elena Kochkina

Visiting Research Fellow, The Alan Turing Institute and Postdoctoral Research Assistant, QMUL

Nicole Peinelt

Nicole Peinelt

Former Doctoral Student

Dr Giovanni Colavizza

Dr Giovanni Colavizza

Feng Shi

Imperial College London

Contact info

[email protected]

External researchers

Radoslaw Kowalski, UCL
Pasquale Minervini, UCL
Andrew Moore, Lancaster University
Marek Rei, University of Cambridge

research_publications

Diachronic word embeddings from 19th-century British newspapers

Diachronic word embeddings trained on a 4.2-billion-word corpus of 19th-century British newspapers, using Word2Vec...

Pedrazzini, Nilo & Barbara McGillivray. (2022). Diachronic word embeddings from 19th-century British newspapers [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7181682

research_publications

Data Study Group Final Report: The National Archives, UK

Discovering topics and trends in the UK government web archive

Data Study Group team. (2021, June 18). Data Study Group Final Report: The National Archives, UK. Zenodo. https://doi.org/10.5281/zenodo.4981184

research_publications

Aiming beyond the Obvious - Identifying Non-Obvious Cases in Semantic Similarity Datasets

Existing datasets for scoring text pairs in terms of semantic similarity contain instances whose...

Nicole Peinelt, Maria Liakata, Dong Nguyen (2019): Aiming beyond the Obvious - Identifying Non-Obvious Cases in Semantic Similarity Datasets. Proceedings of the 57th Conference of the Association for Computational Linguistics (ACL 2019), pages 2792 - 2798.

research_publications

tBERT – Topic Models and BERT Joining Forces for Semantic Similarity Detection

Semantic similarity detection is a fundamental task in natural language understanding. Adding topic information...

Nicole Peinelt, Dong Nguyen, Maria Liakata (2020): tBERT - Topic Models and BERT Joining Forces for Semantic Similarity Detection. Proceedings of the 58th Conference of the Association for Computational Linguistics (ACL 2020), pages 7047-7055.

research_publications

An agenda for research into online hate

Online hate is a ‘wicked problem’ in the truest sense: it is difficult to...

research_publications

Development of a speech quality database under uncontrolled conditions

Objective audio quality assessment is preferred to avoid time-consuming and costly listening tests. The...

A. Ragano, E. Benetos, and A. Hines, "Development of a speech quality database under uncontrolled conditions", in Proc. 21st Annual Conference of the International Speech Communication Association (INTERSPEECH), Oct. 2020.

research_publications

Data Study Group Final Report: WWF

Smart monitoring for conservation areas

Data Study Group team. (2020, June 5). Data Study Group Final Report: WWF. Zenodo. http://doi.org/10.5281/zenodo.3878457

research_publications

Resolving Places, Past and Present: Toponym Resolution in Historical British Newspapers Using Multiple Resources

Newspapers and their metadata are richly geographical, not only in their distribution but also...

Coll Ardanuy, Mariona & McDonough, Katherine & Krause, Amrey & Wilson, Daniel & Hosseini, Kasra & Strien, Daniel. (2019). Resolving places, past and present: toponym resolution in historical british newspapers using multiple resources. GIR '19: Proceedings of the 13th Workshop on Geographic Information Retrieval. 1-6. 10.1145/3371140.3371143.

research_publications

Assessing the Impact of OCR Quality on Downstream NLP Tasks

A growing volume of heritage data is being digitized and made available as text...

van Strien, D.; Beelen, K.; Ardanuy, M.; Hosseini, K.; McGillivray, B. and Colavizza, G. (2020). Assessing the Impact of OCR Quality on Downstream NLP Tasks. In Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 1: ARTIDIGH, ISBN 978-989-758-395-7, pages 484-496. DOI: 10.5220/0009169004840496

research_publications

Data Study Group Final Report: Spend Network

Automated matching of businesses to government contract opportunities

Data Study Group team. (2019, November 29). Data Study Group Final Report: Spend Network. Zenodo. http://doi.org/10.5281/zenodo.3558243

research_publications

A Distributional Semantic Methodology for Enhanced Search in Historical Records: A Case Study on Smell

In this paper we present a methodology based on distributional semantic models that can...

McGregor, S. and McGillivray, B. (2018). A Distributional Semantic Methodology for Enhanced Search in Historical Records: A Case Study on Smell. Proceedings of the 14th Conference on Natural Language Processing (KONVENS 2018) Vienna, Austria, September 19-21, 2018. Austrian Academy of Sciences Press.

research_publications

A Deep Learning Framework for Pricing Financial Instruments

We propose an integrated deep learning architecture for the stock movement prediction. Our architecture...

Wu, Qiong; Zhang, Zheng; Pizzoferrato, Andrea; Cucuringu, Mihai; Liu, Zhenming. "A Deep Learning Framework for Pricing Financial Instruments", arXiv:1909.04497 (2019)

research_publications

Mining the UK Web Archive for Semantic Change Detection

Semantic change detection (i.e., identifying words whose meaning has changed over time) started emerging...

Tsakalidis, A., Bazzi, M., Cucuringu, M., Basile, P., & McGillivray, B. Mining the UK Web Archive for Semantic Change Detection. Proceedings of INTERNATIONAL CONFERENCE RECENT ADVANCES IN NATURAL LANGUAGE PROCESSING, https://doi.org/10.17863/CAM.43534

research_publications

Data Study Group Final Report: NCSC

Capturing the purpose of websites

Data Study Group team. (2019, August 13). Data Study Group Final Report: NCSC. Zenodo. http://doi.org/10.5281/zenodo.3367414

research_publications

Challenges and frontiers in abusive content detection

Online abusive content detection is an inherently difficult task. It has received considerable attention...

B. Vidgen, A. Harris, D. Nguyen, R. Tromble, S. Hale and H. Margetts. Challenges and frontiers in abusive content detection. To appear at the 3rd Workshop on Abusive Language Online at ACL 2019.

research_publications

Unsupervised Acquisition of Verb Subcategorization Frames from Shallow-Parsed Corpora

In this paper, we reported experiments of unsupervised automatic acquisition of Italian and English...

Lenci, A., McGillivray, B., Montemagni, S., and Pirrelli, V. (2008), Unsupervised Acquisition of Verb Subcategorization Frames from Shallow-Parsed Corpora. In Proceedings of the Sixth International Language Resources and Evaluation (LREC’08), Marrakech

research_publications

Semantic structure from Correspondence Analysis

A common problem for clustering tech- niques is that clusters overlap, which makes graphing...

McGillivray, B., Johansson, C., and Apollon, D. (2008). Semantic structure from Correspondence Analysis. In Proceedings of the Workshop on Graph-based Algorithms for Natural Language Processing (COLING 2008), Manchester

research_publications

Selectional Preferences from a Latin Treebank

We present a system that automatically induces Selectional Preferences (SPs) for Latin verbs from...

McGillivray, B. (2009). Selectional Preferences from a Latin Treebank. In Przepiórkowski A., M. Passarotti, S. Raynaud, and F. van Eynde (eds.) Proceedings of the Eighth International Workshop on Treebanks and Linguistic Theories (TLT8). Milan: EDUCatt

research_publications

The Development of the Index Thomisticus Treebank Valency Lexicon.

We present a valency lexicon for Latin verbs extracted from the Index Thomisticus Tree-...

McGillivray, B. and Passarotti, M. (2009). The Development of the Index Thomisticus Treebank Valency Lexicon. In Proceedings of the Workshop on Language Technology and Resources for Cultural Heritage, Social Sciences, Humanities, and Education, Athens

research_publications

Automatic Selectional Preference Acquisition for Latin verbs

We present a system that automatically induces Selectional Preferences (SPs) for Latin verbs from...

McGillivray, B. (2010). Automatic Selectional Preference Acquisition for Latin verbs. In Proceedings of the ACL 2010 Student Research Workshop , Uppsala

research_publications

Accessing and using a corpus-driven Latin Valency Lexicon

McGillivray, B. and Passarotti, M. (2015). Accessing and using a corpus-driven Latin Valency Lexicon. In Haverling, G. (Ed.), Latin linguistics in the early 21st century. Acts of the 16th international colloquium on Latin linguistics, Uppsala, June 6th-11th, 2011, Uppsala

research_publications

Exploiting the Web for Semantic Change Detection

Detecting significant linguistic shifts in the meaning and usage of words has gained more...

Basili, P. and McGillivray, B. (2018). Exploiting the Web for Semantic Change Detection. In 21st International Conference, DS 2018, Limassol, Cyprus, October 29-31, 2018, Proceedings

research_publications

A Distributional Semantic Methodology for Enhanced Search in Historical Records

A Case Study on Smell

McGregor, S. and McGillivray, B. (2018). A Distributional Semantic Methodology for Enhanced Search in Historical Records: A Case Study on Smell. Proceedings of the 14th Conference on Natural Language Processing (KONVENS 2018) Vienna, Austria, September 19-21, 2018. Austrian Academy of Sciences Press.

research_publications

Tools for historical corpus research, and a corpus of Latin

We present LatinISE, a Latin corpus for the Sketch Engine. LatinISE consists of Latin...

McGillivray, B. and Kilgarriff, A. (2013). Tools for historical corpus research, and a corpus of Latin. In Paul Bennett, Martin Durrell, Silke Scheible, Richard J. Whitt (eds.), New Methods in Historical Corpus Linguistics , Tübingen: Narr.

research_publications

Metodi in linguistica computazionale latina

McGillivray, B. (2015). Metodi in linguistica computazionale latina. In Molinelli, P., Putzu, I. (Eds.), Modelli epistemologici, metodologie della ricerca e qualità del dato. Dalla linguistica storica alla sociolinguistica storica . Milan: FrancoAngeli.

research_publications

Making sense through correspondence

McGillivray, B. and Johansson, C. (2009). Making sense through correspondence. Arena Romanistica, vol. 4

research_publications

Quantitative Historical Linguistics.

A Corpus Framework

Jenset, G. B. and McGillivray, B. (2017). Quantitative Historical Linguistics. A Corpus Framework, Oxford: Oxford University Press.

research_publications

Data Study Group Final Report: Global bank

Machine learning for predicting and mitigating operational risk

Data Study Group team. (2019). Data Study Group Final Report: Global bank. http://doi.org/10.5281/zenodo.2557809

research_publications

Getting to Hearer-old: Charting Referring Expressions Across Time

When a reader is first introduced to an entity, its referring expression must describe...

Ieva Staliunaite, Hannah Rohde, Bonnie Webber and Annie Louis, "Getting to Hearer-old: Charting Referring Expressions Across Time", Proceedings of Empirical Methods in Natural Language Processing 2018

research_publications

The University of Edinburgh’s Neural MT Systems for WMT17

This paper describes the University of Edinburgh's submissions to the WMT17 shared news translation...

Sennrich, R, Birch-Mayne, A, Currey, A, Germann, U, Haddow, B, Heafield, K, Miceli Barone, A & Williams, P 2017, The University of Edinburgh’s Neural MT Systems for WMT17. in EMNLP 2017: The Second Conference on Machine Translation, Volume 2: Shared Task Papers.. Association for Computational Linguistics (ACL), pp. 389-399, Proceedings of the Second Conference on Machine Translation, Copenhagen, Denmark, 7-8 September. DOI: 10.18653/v1/W17-4739

research_publications

Emo, love and god: making sense of Urban Dictionary, a crowd-sourced online dictionary

The Internet facilitates large-scale collaborative projects and the emergence of Web 2.0 platforms, where...

Nguyen, D, McGillivray, B & Yasseri, T 2018, 'Emo, love and god: making sense of Urban Dictionary, a crowd-sourced online dictionary' Royal Society Open Science, vol 5, pp. 1-16. DOI: 10.1098/rsos.172320

research_publications

Uncovering Wireless Blackspots using Twitter Data

Blackspots are areas of poor signal coverage or service delivery that leads to customer...

Guo, W.; Zhang, J.: 'Uncovering wireless blackspots using Twitter data', Electronics Letters, 2017, 53, (12), p. 814-816, DOI: 10.1049