John Mcnaught, MA (Hons) (Aberdeen), MA (Manchester)

Postgraduate opportunities

Postgraduate research

I no longer accept any more students.

Numerous PhD, MPhil and MSc students have enriched my research over the years, on topics varying from crosslingual study of text types using principal component analysis, to multidimensionality in concept representations, to automatic term extraction, to machine learning of template extraction rules, to design of onomasiological dictionaries and term banks, to improving software project management through ontology-driven text mining, to text simplification as assistive technology, to named entity recognition and opinion mining for Arabic, ...

The National Centre for Text Mining offers a rich text mining research environment. Academic staff there are primarily looking for research students interested in text mining topics, although would certainly welcome students interested in research in related areas of natural language processing.

They normally would expect research students to be computer literate and to be able to program, or at least to be at home with computational linguistic formalisms, natural language processing workflow frameworks,  deep learning for natural language processing, etc., and, for PhD level study, to have previously studied some aspects of text mining or natural language processing.

If you are interested in being supervised by academic staff in NaCTeM for doctoral or MPhil research, please send them your research proposal. Please consult our information on how to apply for PhD or MPhil.

If you are interested in investigating text mining techniques, say, in relation to a specific application domain, such as biology, the social sciences, or the humanities, then do please contact them. We work very closely with colleagues in other domains, especially the three mentioned, and the text mining research environment here is very conducive to interdisciplinary and cross-disciplinary research.

Postgraduate taught MSc

The School of Computer Science has a number of  taught MSc programmes in Advanced Computer Science. One of the major themes available within this programme is Making Sense of Complex Data, which includes a course unit on  Text Mining.

Keywords (ACM Computing Classification System)

• H.3.1 content analysis and indexing
• H.3.3 information search and retrieval
• H.3.5 online information services
• H.5.2 user interfaces
• I.2.4 knowledge representation formalisms and methods
• I.2.6 learning
• I.2.7 natural language processing
• I.5.3 clustering
• I.5.4 applications (text processing)
• I.5.5 implementation
• I.7.2 document preparation
• J.3 life and medical sciences
• J.4 social and behavioral sciences
• J.5 arts and humanities

Related links

• The National Centre for Text Mining
• Manchester Institute of Biotechnology

Research group

• Text Mining

Research institutes

• Manchester Institute of Biotechnology

• Text mining: information extraction (named entity recognition, term extraction, relation extraction, fact and event extraction: application areas in many fields, e.g. life sciences, health, humanities, social sciences)
• Metadata extraction and exploitation for digital repositories, archives, publishers' content
• Semantic search based on text mining and ontologies
• Aids for authors, systematic reviewers, clinicians constructing clinical trial protocols
• Construction/exploitation of computational language resources: annotated corpora, computational lexica, computational terminologies, ontologies, computational grammars
• Sublanguages: terminology, text types, sublanguage grammar, domain-specific adaptation
• Multilingual language technology
• Infrastructures for computational processing of human language
• Reusability of linguistic resources and NLP components

My research is conducted in an engineering perspective and typically within collaborative research projects, especially ones funded by the European Commission (I have participated in numerous such projects) and via commissioned projects funded by industry (particularly the publishing industry).

Having been a member of academic staff for many years, I then became a Research Fellow from August 2018 to September 2019, when I retired. I now have an honorary appointment in the Department of Computer Science, and continue to be Deputy Director of the National Centre for Text Mining (NaCTeM). I no longer accept any more PhD students.

I have been working in the general area of natural language processing since 1979, which I came to through previous studies in language and linguistics. Until 2000, I was with the Department of Language Engineering (and its Centre for Computational Linguistics) at UMIST, when I transferred to UMIST's Department of Computation. In 2004, UMIST and the Victoria University of Manchester came together to form the University of Manchester.

For many years, I worked on machine translation (MT) aspects, specifically on MT software design, on sublanguage-based MT, and on computational dictionaries. Multilingual issues and sublanguage concerns also brought me to develop strong interests in computational terminology and the representation of special knowledge. From the mid-80s on, I became involved in various language engineering standardisation initiatives such as EAGLES and ISLE. These focussed particularly on issues of reusability of language resources such as text corpora and electronic dictionaries, and design for reuse.

In the latter half of the 90s, I moved into the area of information extraction, working on ontology-driven information extraction, and then more broadly on text mining.

In September 2004, the National Centre for Text Mining (NaCTeM) was established. This was the first publicly funded national centre for text mining in the world and reflects thus the depth and breadth of text mining expertise here in the university. It is hosted by the School of Computer Science but is located in the Manchester Institute of Biotechnology. NaCTeM participates in several networks such as FLaReNet and Meta-Net, and has been heavily involved in collaborating with other partners in delivering OpenMinTed (the Open Mining Infrastructure for Text and Data).