Homepage of Harald Hammarström
Photo by Marcin Zalewski using Aslan Askarov's Camera
Harald Hammarstrom
I am a PhD Student working in the Language Technology Group
at Chalmers University.
I used to be working with grammars for number words across various
languages but now I'm looking at unsupervised morphology induction and
lexicon generation from corpora. My supervisor is the erudite Bengt Nordström.
Since 1996 and forever more I am a Python Programmer.
Teaching
Workshop on Unsupervised Methods in NLP
- I am co-organizing (with Magnus Rosell and Sumithra Velupillai)
a workshop on Unsupervised Methods in NLP
hosted at SLTC '08, Stockholm 20-21 November 2008.
Gothenburg Typological Seminars
- I am the "spokesperson" for the GTS seminar series. Here is the schedule.
Personal and Fun Stuff
- NEW FAQ about my hair.
- (OLD FAQ about my hair.)
- A CV
- Old Pictures of me with some top class academics.
- Old Pictures of me with some bottom class non-academics.
- My Record Collection.
- My friend Tomas grew a mustache and, a random day when he was 23, sent in this fake birthday ad to Swedish biggest morning paper.
Contact information
Interests
- Number Theory
- Empirical Linguistics
- Artifical Intelligence
- Political Economy
- Computational Linguistics
- Linguistic Typology
- Vegan Nutrition
- Chess
- And many other things...
|
Disinterests
- Classical Music
- Sociolinguistics in the Western World
- Generative Linguistics
- Software Engineering
- Concurrent Programming
- The Weather
- Mainstream History
- Monologue or Dialogue Systems
- And many other things...
|
Publications/Conference Presentations/Theses/Reports etc. (.pdf)
- H. Hammarström 2009 Unsupervised Learning of Morphology and the Languages of the World. (.pdf) Thesis for the Degree of Doctor of Engineering,
Department of Computer Science and Engineering, Chalmers University. 284 pp.
- H. Hammarström 2009 Poor man's word-segmentation: Unsupervised morphological analysis for Indonesian. (pre-pub draft .pdf) Proceedings of the Third International Workshop on Malay and
Indonesian Language Engineering (MALINDO). Singapore: ACL.
- H. Hammarström 2009 Whence the Kanum base-6 Numeral System?. (pre-pub draft .pdf) Linguistic Typology 13(2):305-319.
- H. Hammarström 2009 Whence the Kanum base-6 Numeral System?. (pre-pub draft .pdf) Linguistic Typology 13(2):305-319.
- H. Hammarström 2009 Sampling and Genealogical Coverage in the WALS. (pre-pub draft .pdf, pre-pub draft appendix .pdf)) Linguistic Typology 13(1):105-119, plus 198pp appendix.
- H. Hammarström 2009 Rarities in Numeral Systems. (ms .pdf) In: Jan Wohlgemuth and Michael Cysouw (eds.) Rara and Rarissima: Collecting and interpreting unusual characteristics of human languages [Empirical Approaches to Language Typology], pp. 7-55, MOUTON.
- H. Hammarström 2008 Counting Languages in Dialect Continua Using the Criterion of Mutual Intelligibility. (ms .pdf) Journal of Quantitative Linguistics 15(1), pp. 36-45.
- H. Hammarström, Christina Thornell, Malin Petzell and Torbj\"orn Westerlund 2008 Bootstrapping Language Description: The case of Mpiemo (Bantu A, Central African Republic). (.pdf) In: Proceedings of LREC-2008, pp. 3350-3554. European Language Resources Association (ELRA).
- H. Hammarström 2008 Review of Rabha, U. V. Joseph, BRILL, 2008. [Languages of the Greater Himalayan Region 1]. (.pdf), Himalayan Linguistics Review 9:1-3, 2009.
- Harald Hammarstr\"om 2008 Automatic Annotation of Bibliographical References with Target Language (pre-pub. draft .pdf) Proceedings of MMIES-2: Multi-source, Multilingual Information Extraction and Summarization, Manchester, 23 August, 2008
- H. Hammarström 2007 Unsupervised Learning of Morphology: Survey, Model, Algorithm and Experiments. (.pdf) Thesis for the Degree of Licentiate of Engineering,
Department of Computer Science and Engineering, Chalmers University. 91 pp.
- H. Hammarström 2007 A Survey and Classification of Methods for (Mostly) Unsupervised Learning of Morphology. (.pdf) In: Proceedings of NODALIDA 2007, the 16th Nordic Conference of Computational Linguistics, Tartu, Estonia, 25-26 May 2007, NEALT.
- H. Hammarström 2007 A Fine-Grained Model for Language Identification. (.pdf) In: Proceedings of {iNEWS}-07 Workshop at SIGIR 2007, 23-27 July 2007, Amsterdam, pp. 14-20, ACM.
- M. Humayoun, H. Hammarstr\"om, and A. Ranta. Urdu Morphology, Orthography and Lexicon Extraction. (pre-pub. draft .pdf) CAASL-2: The Second Workshop on Computational Approaches to Arabic Scriptbased
Languages, July 21-22, 2007, LSA 2007 Linguistic Institute, Stanford University. 2007.
- H. Hammarström 2007 Handbook of Descriptive Language Knowledge: A Full-Scale Reference Guide for Typologists. (pre-pub. draft .pdf). LINCOM Handbooks in Linguistics 22, LINCOM. 312 pp.
- H. Hammarström 2006 Review of Lithuanian Romani, Anton Tenser, Lincom, 2005. [Languages of the World/Materials 452]. (.pdf, .html) LINGUIST LIST 17.1511 16 May 2006.
- H. Hammarström 2006 Poor Man's Stemming: Unsupervised Recognition of Same-Stem Words. (pre-pub. draft .pdf)
In: Ng, Hwee Tou and Leong, Mun-Kew and Kan, Min-Yen and Ji, Donghong
(eds.) Information Retrieval Technology: Proceedings of the Third Asia
Information retrieval Symposium, AIRS 2006, Singapore, October 2006,
pp. 323-337, SPRINGER, LNCS 4182.
- H. Hammarström 2006 A Naive Theory of Morphology and an Algorithm for Extraction. (.pdf)
In R. Wicentowski and G. Kondrak (eds.) SIGPHON 2006: Eighth Meeting of
the Proceedings of the ACL Special Interest Group on Computational
Phonology, 8 June 2006, New York City, USA}, pp. 79-88, Association for
Computational Linguistics. NOTE: This is a revised version from the one
in the printed proceedings since there was a grave error in the printed
one. I was told that this revised version would appear on the ACL
website but this seems not to have happened (I don't know the reason
why).
- M. Forsberg, H. Hammarström and A. Ranta 2006 Lexicon Extraction from Raw Text Data. (pre-pub. draft .pdf).
In:
Salakoski, T. and Ginter, F. and Pyysalo, S. and Pahikkala, T. (eds.)
Advances in Natural Language Processing: Proceedings of the 5th
International Conference, FinTAL 2006 Turku, Finland, August 23-25,
2006, pp. 488-499, SPRINGER, LNCS 4139.
- H. Hammarström 2006 Review of Some Aspects of the Grammar of
Zina Kotoko, Bodil Kappel; Odden, David; Holmberg, Anders (eds.),
Lincom, 2002. [LINCOM Studies in African Linguistics 54]. (.pdf, .html) LINGUIST LIST 17.818 16 March 2006.
- H. Hammarström 2006 Complexity in Numeral Systems with an Investigation into Pidgins, Pidgincreoles and Creoles. (draft .pdf)
to appear in Miestamo, Matti, Kaius Sinnemäki and Fred Karlsson (eds).
Submitted. Language Complexity: Typology, Contact, Change [Studies in
Language Companion Series]. Amsterdam: John Benjamins.
- H. Hammarström 2005 A New Algorithm for Unsupervised Induction of Concatenative Morphology. (.pdf, .ps a0 size) Poster presented at
FINITE STATE
METHODS IN NATURAL LANGUAGE PROCESSING (FSMNLP '05),
1-2 Sept 2005, Helsinki. In: Finite State Methods in Natural Language
Processing: 5th International Workshop, FSMNLP 2005, Helsinki, Finland,
September 1-2, 2005. Revised Papers, pp. 288-289, SPRINGER, LNCS 4002.
- H. Hammarström 2005 Review of the Ethnologue, 15th Ed., Raymond J. Gordon (ed.), SIL International, Dallas, 2005. (.pdf, .html) LINGUIST LIST 16.2637 12 Sept 2005.
- H. Hammarström 2004 Number Bases, Frequencies and Lengths Cross-Linguistically. (.pdf) Abstract accepted to LINGUISTIC PERSPECTIVES ON NUMERICAL EXPRESSIONS, 10-11 June 2004, Utrecht, Netherlands. Draft (.ps) of full paper. I don't know when/where/if the full paper will be finished and appear somewhere.
- H. Hammarström 2004 Deduction of Numeral Grammars. (.pdf)
In Paul Egré and Laura Alonso i Alemany (Eds.) Proceedings of the Ninth
ESSLLI Student Session, August 2004, Nancy, France. Full proceedings
available here.
- H. Hammarström 2004 Properties of Lower Numerals and their Explanation: A Reply to Pawel/ Rutkowski. (pre-pub. draft .pdf ) in Journal of Universal Language 5:2, 2004, pp. 1-20.
- H. Hammarström 2002 Shallow Reasoning on Open-Domain Texts. (.pdf), Master's Thesis, Department of Computer Science, Uppsala University, 2002.
- H. Hammarström 2002 Overview of IT-based Tools for Learning and Training Grammar (.pdf),
Project Report, Department of Linguistics, Uppsala University, 2002.
Since this is from 2002 it is now more of a historical document.
Bibliographies
|