Home Catalogue search

eng

Refine your search:

Search in the Catalogues and Directories






	Sort by
Simple Search

Hits 1 – 11 of 11

1	Modeling Inflectional Complexity in Natural Language Processing
	Nicolai, Garrett J. - : University of Alberta. Department of Computing Science., 2017
	Abstract: Degree: Doctor of Philosophy ; Abstract: Inflectional morphology presents numerous problems for traditional computational models, not least of which is an increase in the number of rare types in any corpus. Although few annotated corpora exist for morphologically complex languages, it is possible for lay-speakers of the language to generate data such as inflection tables that describe patterns that can be learned by machine learning algorithms. We investigate four inflectional tasks: inflection generation, stemming, lemmatization, and morphological analysis, and demonstrate that each of these tasks can be accurately modeled using sequential string transduction methods. Furthermore, expert annotation is unnecessary: inflectional models are learned from crowd-sourced inflection tables. We first investigate inflection generation: given a dictionary form and a tag representing inflectional information, we produce inflected word-forms. We then refine our predictions by referring to the other forms within a paradigm. Results of experiments on six diverse languages with varying amounts of training data demonstrate that our approach improves the state of the art in terms of predicting inflected word-forms. We next investigate stemming: the removal of inflectional prefixes and suffixes from a word. Unlike the inflection generation task, it is not possible to use inflection tables to learn a fully-supervised stemming model; however, we exploit paradigmatic regularity to identify stems in an unsupervised manner with over 85% accuracy. Experiments on English, Dutch, and German show that our stemmers substantially outperform rule-based and unsupervised stemmers such as Snowball and Morfessor, and approach the accuracy of a fully-supervised system. Furthermore, the generated stems are more consistent than those annotated by experts. We also use the inflection tables to learn models that generate lemmas from inflected forms. Unlike stemming, lemmatization restores orthographic changes that have occurred during inflection. These models are more accurate than Morfette and Lemming on most datasets. Finally, we extend our lemmatization methods to produce complete morphological analyses: given a word, return a set of lemma / tag pairs that may have generated it. This task is more ambiguous than inflectional generation or lemmatization which typically produce only a small number of outputs. Thus, morphological analysis involves producing a complete list of lemma+tag analyses for a given word-form. Experiments on four languages demonstrate that our system has much higher coverage than a hand-engineered FST analyzer, and is more accurate than a state-of-the-art morphological tagger.
	Keyword: Computational Linguistics; Inflection; Morphology; Natural Language Processing; String Transduction
	URL: https://era.library.ualberta.ca/items/c19e53ed-60b2-4742-bb6a-01f5683de6a0 https://doi.org/10.7939/R3HT2GR63 http://hdl.handle.net/10402/era.44191
	BASE
	Hide details

2	to appear). Semi-supervised learning of morphological paradigms and lexicons
	Malin Ahlberg; Markus Forsberg; Mans Hulden
	In: http://aclweb.org/anthology//E/E14/E14-1060.pdf (2014)
	BASE
	Show details

3	Parallel MultiTheory Annotations of Syntactic Structure
	Jerid Francom; Mans Hulden
	In: http://www.lrec-conf.org/proceedings/lrec2008/pdf/587_paper.pdf (2008)
	BASE
	Show details

4	POS-tag based poetry generation with WordNet
	Manex Agirrezabal; Bertol Arrieta; Aitzol Astigarraga...
	In: http://wing.comp.nus.edu.sg/~antho/W/W13/W13-2121.pdf
	BASE
	Show details

5	ZeuScansion: a tool for scansion of English poetry
	Manex Agirrezabal; Bertol Arrieta; Aitzol Astigarraga...
	In: http://www.aclweb.org/anthology/W/W13/W13-1803.pdf
	BASE
	Show details

6	using a
	Mans Hulden; Iñaki Alegria; Izaskun Etxeberria...
	In: http://www.aclweb.org/anthology-new/W/W11/W11-2605.pdf
	BASE
	Show details

7	Finite state applications with Javascript
	Mans Hulden; Miikka Silfverberg; Jerid Francom
	In: http://emmtee.net/oe/nodalida13/conference/91.pdf
	BASE
	Show details

8	Foma: a finite-state compiler and library
	Mans Hulden
	In: http://aclweb.org/anthology/E/E09/E09-2008.pdf
	BASE
	Show details

9	Revisiting multi-tape automata for Semitic morphological analysis and generation
	Mans Hulden
	In: http://aclweb.org/anthology-new/W/W09/W09-0803.pdf
	BASE
	Show details

10	Using foma for language-based games
	Manex Agirrezabal; Iñaki Alegria; Mans Hulden
	In: http://ixa.si.ehu.es/Ixa/Argitalpenak/Artikuluak/1349278797/publikoak/pdf/
	BASE
	Show details

11	ACTIV-ES: a comparable, cross-dialect corpus of 'everyday' Spanish from Argentina, Mexico, and Spain
	Jerid Francom; Mans Hulden; Adam Ussishkin
	In: http://www.lrec-conf.org/proceedings/lrec2014/pdf/691_Paper.pdf
	BASE
	Show details

© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern