Dr Rachele De Felice

Teaching Fellow at the Department of English Language and Literature at UCL.


Education and Experience

  • Leverhulme Early Career Research Fellow at Centre for Research in Applied Linguistics at the University of Nottingham, working on the pragmatics of Business English emails
  • Postdoctoral Research Fellow at Educational Testing Service (Princeton, New Jersey), working on automated identification of speech acts in emails, and on automated scoring of open score content test answers
  • DPhil (PhD) in Computational Linguistics at Oxford University (Department of Computer Science), working on automatic error detection in non-native English writing, using models which can predict what preposition or determiner is most likely to occur in a given context
  • MPhil in Linguistics (Computational Linguistics, Semantics, Theory of Translation), and BA in English literature, Oxford University
  • full CV [pdf]
  • Teaching

    As a Teaching Fellow on the MA in English Linguistics at UCL, I convene the modules on English Phonetics and Phonology and English Language in Use, and I contribute to the module on English Corpus Linguistics. I also contribute to the undergraduate course on Modern English Language.

    Previously, I have taught modules on Intercultural Communication, Pragmatics, Theory of Translation, General Linguistics, and Computational Linguistics.


    My research is in the field of corpus pragmatics. It focuses on speech act annotation and the creation of pragmatic profiles of Business English by applying corpus analysis and natural language processing (NLP) techniques to large collections of real-world data. It addresses the following questions:

    • What are the main pragmatic characteristics of Business English?
    • Are there significant pragmatic variations in spoken, written, and email Business English?
    • How do these findings compare to the pragmatic features of other types of communication, such as everyday conversation?

    The techniques used to extract pragmatic profiles can also be adapted to further our understanding of communication in other specialised domains such as social work or health communication, addressing issues such as the pragmatic strategies used in presenting upsetting information, or in interacting with patients of different ages.

    My postdoctoral research project focused on understanding pragmatic content of short texts, especially those written by learners of English, for the ultimate goal of automated assessment. In particular, I looked at emails in a workplace context, to see whether it is possible to automatically recognise the speech acts contained in each sentence by relying on a combination of lexical and syntactic features. The data collected and analysed for this research also offers insights into the patterns preferred by L2 English learners in formulating speech acts, which can be compared to L1 models.


    Rachele De Felice (2013). A corpus-based classification of commitments in Business English. in J. Romero-Trillo (ed.), Yearbook of Corpus Linguistics and Pragmatics 2013, pp.153-171 [link]

    Rachele De Felice, Jeannique Darby, Anthony Fisher, and David Peplow (2013). A classification scheme for annotating speech acts in a business email corpus. ICAME Journal 37, pp.71-105 [link]

    Rachele De Felice and Paul Deane (2012). Identifying speech acts in e-mails: Toward automated scoring of the TOEIC(R) e-mail task (ETS Research Report No. RR-12-16). Princeton, NJ: ETS [full report pdf]

    Rachele De Felice (2011). Giving advice; Giving opinions; Making commitments; Making requests; Negotiating. In S. O'Shea et al. (Eds.), Cambridge Business English Dictionary. Cambridge: Cambridge University Press

    Rachele De Felice and Stephen G Pulman (2009). Automatic detection of preposition errors in learner writing. CALICO Journal 26(3) (Special Issue of the 2008 CALICO Workshop on Automatic Analysis of Learner Language) [pdf]

    Rachele De Felice and Stephen G Pulman (2008). A classifier-based approach to preposition and determiner error correction in L2 English. Proceedings of COLING, Manchester, United Kingdom [pdf]

    Rachele De Felice and Stephen G Pulman (2007). Automatically acquiring models of preposition use. Proceedings of the ACL-07 Workshop on Prepositions, Prague, Czech Republic [pdf]

    Rachele De Felice and Stephen G Pulman (2006). Using clustering to improve adjective selection in English adjective-noun pairs. Proceedings of the XL Conference of the Societa' di Linguistica Italiana, Vercelli, Italy [abstract pdf][full paper pdf]

    PhD thesis: Automatic error detection in non-native English

    Conference presentations and full list of publications available here.

    This page last modified 1 December, 2016 by Survey Web Administrator.