Skip to main content
   
Andrew Roberts @ School of Computing

Research

My research focuses mainly within the field of Natual Language Learning. More specifically, my PhD will look at developing techniques for efficient and accurate grammar induction systems. My supervisor is Eric Atwell.

Previous work looked at employing clustering techniques for unsupervised learning of parts-of-speech. I was fortunate enough to have collaborated with John Elliott - who is a well established researcher in unsupervised language learning.

I've recently become very interested in Arabic computional linguistics. I've developed a couple of tools, including aConCorde, an Arabic concordancer, and a program for converting between Buckwalter transliteration system and Unicode. I'm interested in standard CL tools like stemmers, taggers and parsers too.

Publications

2006
Roberts Andrew, Al-Sulaiti, Latifa and Atwell, Eric
aConCorde: Towards an open-source, extendable concordancer for Arabic
In: McEnery, Tony et al. (eds.) Corpora Journal. 1(1). Edinburgh University Press. Forthcoming
pdf | bibtex
Atwell, Eric and Roberts, Andrew
Combinatory hybrid elementary analysis of text
Kurimo, M, Creutz, M and Lagus, K (eds.) Proceedings of the PASCAL Challenge Workshop on Unsupervised Segmentation of Words into Morphemes.
pdf | bibtex
2005
Al-Sulaiti, Latifa, Roberts, Andrew and Atwell, Eric.
The use of Corpora and Concordance in the Teaching of Contempory Arabic.
Proceedings of EuroCALL 2005, Cracow, Poland.
(forthcoming)
Roberts, Andrew, Al-Sulaiti, Latifa and Atwell, Eric.
aConCorde: Towards a Proper Concordance of Arabic
Proceedings of the Corpus Linguistics 2005 Conference, Birmingham, UK.
pdf | poster (pdf) | bibtex
Abu Shawar, Bayan, Atwell, Eric and Roberts, Andrew.
FAQChat as an Information Retrieval System
In: Vetulani, Zygmunt (ed.) Human Language Technologies as a Challenge. Proceedings of the 2nd Language and Technology Conference, Wydawnictwo Poznanskie, Poznan, Poland, pp.274-278. 2005
pdf
2004
van Zaanen, Menno; Roberts, Andrew and Atwell, Eric.
A Multilingual Parallel Parsed Corpus as Gold Standard for Grammatical Inference Evaluation
The Amazing Utility of Parallel and Comparable Corpora Workshop. LREC 2004. Lison, Portugal. pp 58-61, 2004.
ps.gz | pdf | bibtex
2003
Roberts, Andrew
CL2003: the International Conference on Corpus Linguistics.
ELSnews newsletter of the European Language and Speech Network, vol. 12.2, pp.6-7, 2003
ps.gz | pdf | bibtex
Atwell, Eric; Abu Shawar, Bayan; Babych, Bogdan; Elliott, Debbie; Elliott, John; Gent, Paul; Hartley, Anthony; Hu, Xunlei Rose; Medori, Julia; Oba, Toshifumi; Roberts, Andrew; Scharoff, Serge; Souter, Clive
Corpus Linguistics, Machine Learning and Evaluation: Views from Leeds.
Research Report number 2003.02. School of Computing, University of Leeds, 2003
pdf | bibtex
Roberts, Andrew and Atwell, Eric
The Use of Corpora for Automatic Evaluation of Grammar Inference Systems.
Proceedings of the Corpus Linguistics 2003 Conference, Lancaster, UK. pp 665-661, 2003.
abstract | pdf | slides (pdf) | bibtex
Roberts, Andrew and Atwell, Eric
Unsupervised Grammar Inference Systems for Natural Language.
DRAFT - Submitted to Pattern Review
abstract | ps.gz | pdf
2002
Roberts, Andrew and Atwell, Eric
Unsupervised Grammar Inference Systems for Natural Language.
Research Report number 2002.20. School of Computing, University of Leeds, 2002
ps.gz | pdf | bibtex
Roberts, Andrew
Automatic Acquisition of Word Classification using Distributional Analysis of Content Words with Respect to Function Words.
School of Computing, University of Leeds, United Kingdom
abstract | ps.gz | pdf | bibtex entry

Programmee committees

  • Special Session on Evolutionary Grammatical Inference (EGI2005) @ 5th International Conference on Intelligent Systems Design and Applications (ISDA2005), Wroclaw, Poland.

Presentations

Others

In my spare time I have been known to submit some articles for technology sites about Linux and Java, amongst other things.
Nedstat Basic - Free web site statistics
Personal homepage website counter