A comparison of two different approaches to morphological analysis of Dutch

Pauw, Guy De; Laureys, Tom; Daelemans, Walter; hamme, Hugo Van

doi:10.3115/1622153.1622161

Cited by 6 publications

(5 citation statements)

References 10 publications

(5 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cast as a classification problem, morpheme boundaries were detected based on letter sequences. De Pauw et al (2004) built on this work and compared a memory-based learning method with a finite state method. One of the characteristic features of Dutch is diminutive formation (Trommelen, 1983) and computational approaches have been explored to predict the correct diminutive suffix in Dutch (Daelemans et al, 1996;Kool et al, 2000).…”

Section: Related Workmentioning

confidence: 99%

Automatic Detection of Intra-Word Code-Switching

Nguyen¹,

Cornips²

2016

Proceedings of the 14th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

View full text Add to dashboard Cite

Welcome to the 14th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology. The workshop aims to bring together researchers interested in applying computational techniques to problems in morphology, phonology, and phonetics. Our program this year highlights the ongoing and important interaction between work in computational linguistics and work in theoretical linguistics. We received 23 submissions and accepted 11.The volume of submissions made it necessary to recruit several additional reviewers. We'd like to thank all of these people for agreeing to review papers on what seemed like impossibly short notice.This year also marks the first SIGMORPHON shared task, on morphological reinflection. The shared task received 9 submissions, all of which were accepted, and greatly advanced the state of the art in this area.We thank all the authors, reviewers and organizers for their efforts on behalf of the community. AbstractThis paper conceptualizes speech prosody data mining and its potential application in data-driven phonology/phonetics research. We first conceptualize Speech Prosody Mining (SPM) in a time-series data mining framework. Specifically, we propose using efficient symbolic representations for speech prosody time-series similarity computation. We experiment with both symbolic and numeric representations and distance measures in a series of time-series classification and clustering experiments on a dataset of Mandarin tones. Evaluation results show that symbolic representation performs comparably with other representations at a reduced cost, which enables us to efficiently mine large speech prosody corpora while opening up to possibilities of using a wide range of algorithms that require discrete valued data. We discuss the potential of SPM using time-series mining techniques in future works. IntroductionCurrent investigations on the phonology of intonation and tones (or pitch accent) typically employ data-driven approaches by building research on top of manual annotations of a large amount of speech prosody data (for example, (Morén and Zsiga, 2006; Zsiga and Zec, 2013), and many others). Meanwhile, researchers are also limited by the amount of resources invested in such expensive endeavor of manual annotations. Given this paradox, we believe that this type of data driven approach in phonology-phonetics interface can benefit from tools that can efficiently index, query, classify, cluster, summarize, and discover meaningful prosodic patterns from a large speech prosody corpus.The data mining of f 0 1 (pitch) contour patterns from audio data has recently gained success in the domain of Music Information Retrieval (aka MIR, see (Gulati and Serra, 2014; Gulati et al., 2015; Ganguli, 2015) for examples). In contrast, the data mining of speech prosody f 0 data (here on referred to as Speech Prosody Mining (SPM) 2 ) is a less explored research topic (Raskinis and Kazlauskiene, 2013). Fundamentally, SPM in a large prosody corpus aims at discovering meaningful patterns in the f ...

show abstract

Section: Related Workmentioning

confidence: 99%

Automatic Detection of Intra-Word Code-Switching

Nguyen¹,

Cornips²

2016

Proceedings of the 14th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

View full text Add to dashboard Cite

show abstract

“…In this section, we describe our data-driven method for morphological analysis of Swahili, which is based on supervised machine learning. It reuses and refines the basic methodology coined in Van den Bosch and Daelemans (1999) which has been successfully applied to morphologically rich(er) languages such as Dutch (De Pauw et al 2004) and Arabic (Van den ). We use the data set described in Section 3 as our primary information source, and describe two systems.…”

Section: Towards a Swahili Morphological Databasementioning

confidence: 99%

“…A typical application of a lemmatizer is integrated in Google's search facility, which automatically lemmatizes a search term like 'discussions' to also produce hits for the word form 'discussion'. Lemmatization is also often used to enhance statistical models of language in other language technology applications, like machine translation (Oflazer 2008) and speech recognition (De Pauw et al 2004). There are however few publications that explicitly discuss the obvious lexicographic application of a lemmatizer, i.e.…”

Section: Computational Morphological Analysismentioning

confidence: 99%

“…Using statistical processing (Masaaki 1999) and/or machinelearning techniques (Van den Bosch and Daelemans 1999), these data-driven methods establish an effective and truly language-independent technique for morphological analysis, that can easily be ported to new domains. Furthermore, manually constructed rule-based analyzers typically do not significantly outperform data-driven approaches in a direct comparison (De Pauw et al 2004).…”

Section: Current Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Improving the Computational Morphological Analysis of a Swahili Corpus for Lexicographic Purposes

Pauw¹,

Schryver²

2009

lex

View full text Add to dashboard Cite

show abstract

“…In case of segmentation tasks such as syllabification, the output symbol set typically consist of a "null" value that signifies that no boundary occurs at the focus input symbol, and one or more positive values marking that some type of boundary does occur at the focus letter. Example morpho-phonological tasks to which memory-based learning has been applied are hyphenation and syllabification (Daelemans & Van den Bosch, 1992); grapheme-to-phoneme conversion (Van den Bosch & Daelemans, 1993;Daelemans & Van den Bosch, 1996); and morphological analysis (Van den Bosch & De Pauw et al, 2004). Although these examples are applied mostly to Germanic languages (English, Dutch, and German), applications to other languages with more complicated writing systems or morphologies, or with limited resources, have also been presented: for example, letter-phoneme Page: 13 job: daelemans-vandenbosch macro: handbook.cls date/time: 12-Jun-2009/15:00 conversion in Scottish Gaelic (Wolters & Van den Bosch, 1997), morphological analysis of Arabic (Marsi et al, 2006), or diacritic restoration in languages with a diacritic-rich writing system (Mihalcea, 2002;De Pauw et al, 2007).…”

Section: Morpho-phonologymentioning

confidence: 99%

Memory‐Based Learning

Daelemans

Bosch

2010

The Handbook of Computational Linguistics and Natural Language Processing

Self Cite

View full text Add to dashboard Cite

Memory-Based Learning 5 2 Memory-Based Language Processing MBL, and its application to NLP, which we will call Memory-Based Language Processing (MBLP) here, is based on the idea that learning and processing are two sides of the same coin. Learning is the storage of examples in memory, and processing is similarity-based reasoning with these stored examples. The approach is inspired by work in pre-Chomskyan linguistics, categorization psychology, and statistical pattern recognition. The main claim is that, contrary to majority belief since Chomsky, generalization (going beyond the data) can also be achieved without formulating abstract representations such as rules.Abstract representations such as rules, decision trees, statistical models, and trained artificial neural networks forget about the data itself, and only keep the abstraction. Such eager learning approaches are usually contrasted with table lookup, a method that obviously cannot generalize. However, by adding similarity-based reasoning to table lookup, lazy learning approaches such as MBL are capable of going beyond the training data as well, and on top of that keep all the data available. This is arguably a useful property for NLP tasks: in such tasks, low-frequency or atypical examples are often not noise to be abstracted from in models, but on the contrary an essential part of the model.In the remainder of this Section, we will describe a particular instantiation of memory-based approaches, MBLP, that we have found to work well for language processing problems and for which we make available open source software (TiMBL). The approach is a combination and extension of ideas from Instance Based Learning (Aha et al., 1991)) and Memory-Based Reasoning

show abstract

A comparison of two different approaches to morphological analysis of Dutch

Cited by 6 publications

References 10 publications

Automatic Detection of Intra-Word Code-Switching

Automatic Detection of Intra-Word Code-Switching

Improving the Computational Morphological Analysis of a Swahili Corpus for Lexicographic Purposes

Memory‐Based Learning

Contact Info

Product

Resources

About