Bootstrapping Morphological Analyzers by Combining Human Elicitation and Machine Learning

Oflazer, Kemal; Ниренбург, Сергей; McShane, Marjorie

doi:10.1162/089120101300346804

Cited by 29 publications

(24 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…a Penn TreeBank POS tag). What they don't yield is a generative model of the language's morphology which would contain information about the position or inflectional classes.Work that is most similar to mine in what it aims for is Oflazer and Gokhan (1996) and Oflazer, Nirenburg and McShane (2001). Oflazer and Gokhan (1996) use constraints to model morphotactics, but the constraints are hand-built and unsupervised learning is used only for segmentation.…”

mentioning

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

mentioning

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

“…Active learning methods have been applied for constructing FST-based analyzers by eliciting new rules from a user with linguistic expertise (Oflazer et al, 2001;Bosch et al, 2008). These development efforts are fast for rule-based systems, but still require months of work.…”

Section: Active Learning Applied To Morphological Segmentationmentioning

confidence: 99%

Low-Resource Active Learning of Morphological Segmentation

Grönroos

Hiovain

Smit

et al. 2016

NEJLT

View full text Add to dashboard Cite

Many Uralic languages have a rich morphological structure, but lack morphological analysis tools needed for efficient language processing. While creating a high-quality morphological analyzer requires a significant amount of expert labor, data-driven approaches may provide sufficient quality for many applications. We study how to create a statistical model for morphological segmentation with a large unannotated corpus and a small amount of annotated word forms selected using an active learning approach. We apply the procedure to two Finno-Ugric languages: Finnish and North Sámi. The semi-supervised Morfessor FlatCat method is used for statistical learning. For Finnish, we set up a simulated scenario to test various active learning query strategies. The best performance is provided by a coverage-based strategy on word initial and final substrings. For North Sámi we collect a set of humanannotated data. With 300 words annotated with our active learning setup, we see a relative improvement in morph boundary F 1 -score of 19% compared to unsupervised learning and 7.8% compared to random selection.

show abstract

“…The learning occurs by approximating the contexts both from specific examples (which may be too narrow) and generalisations (which may be too broad) as context conditions. Oflazer and Nirenburg (1999) and Oflazer et al (2001) present a method for bootstrapping morphological analysers by combining human elicitation and machine learning. Human informants provide the examples used by the machine learning process to deduce rewrite rules necessary for accounting for the data.…”

Section: Past Workmentioning

confidence: 99%

An informal discovery procedure for two-level rules

Koskenniemi

2013

JLM

View full text Add to dashboard Cite

The paper shows how a certain kind of underlying representations (or deep forms) of words can be constructed in a straightforward manner through aligning the surface forms of the morphs of the word forms. The inventory of morphophonemes follows directly from this alignment. Furthermore, the two-level rules which govern the different realisations of such morphophonemes follow fairly directly from the previous steps. The alignment and rules are based upon an approximate general metric among phonemes, e.g., articulatory features, that determines which alternations are likely or possible. This enables us to summarise contexts for the different realisations.

show abstract

Bootstrapping Morphological Analyzers by Combining Human Elicitation and Machine Learning

Cited by 29 publications

References 20 publications

Automatic Detection of Intra-Word Code-Switching

Automatic Detection of Intra-Word Code-Switching

Low-Resource Active Learning of Morphological Segmentation

An informal discovery procedure for two-level rules

Contact Info

Product

Resources

About