Learning in the limit with lattice-structured hypothesis spaces

Heinz, Jeffrey; Kasprzik, Anna; Kötzing, Timo

doi:10.1016/j.tcs.2012.07.017

“…A positive answer would have important repercussions for linguistics as well as natural language processing. The subregular classes identified in computational phonology are learnable in the limit from positive text (Heinz et al, 2012), so a subregular theory of morphology would greatly simplify machine learning while also explaining how morphological dependencies can be acquired by the child from very little input. A subregular model of morphology would also be much more restricted with respect to what processes are predicted to arise in natural languages.…”

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

“…In contrast to regular languages, tier-based strictly local languages are efficiently learnable in the limit from positive text (Heinz et al, 2012;Jardine and Heinz, 2016). Our result thus marks a first step towards provably correct machine learning algorithms for natural language morphology.…”

Section: Resultsmentioning

confidence: 78%

“…The subregular hierarchy includes many other classes (see Fig. 1), but the previous three are noteworthy because they are conceptually simple and efficiently learnable in the limit from positive data (Heinz et al, 2012;Jardine and Heinz, 2016) while also furnishing sufficient power for a wide range of phonological phenomena (Heinz, 2015;Jardine, 2015).…”

Section: Subregular Patterns In Morphologymentioning

confidence: 99%

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

Elsner¹,

Kuebler²

2016

0

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

“…A formal definition of a GIM which learns in this way is provided later in Definition 3. The SL k languages are identifiable in the limit from positive presentations [19] with a poly-time iterative and set-driven learner [20].…”

Section: B Grammatical Inferencementioning

confidence: 99%

“…The rules of the game are: Rule 1: at each round, either no door opens (thus ǫ ∈ Σ2), or one opens and another one closes; Rule 2: doors closed must be opposite to each other, that is, Σ2 = {ad, ae, af, bf, ce, ef, ǫ} where ij, denotes doors i and j being closed. Rule 1 makes L2(G) a strictly 2-local (SL2) language [20], [23]. The graph of this language acceptor can be represented with a Myhill graph.…”

Section: Playing For Realmentioning

confidence: 99%

Adaptive Symbolic Control for Finite-State Transition Systems With Grammatical Inference

Fu

¹

,

Tanner

²

,

Heinz

³

et al. 2014

IEEE Trans. Automat. Contr.

Self Cite

View full text Add to dashboard Cite

Abstract-This note presents an approach that integrates elements from grammatical inference and game theory to address the problem of supervising finite-state transition systems operating in adversarial, partially known, rule-governed environments. The combined formulation produces controllers which guarantee that a transition system satisfies a task specification in the form of a logical formula, if and only (a) the true model of the environment is in the class of models inferable from positive data presentation (observations), (b) a characteristic sample of the environment's behavior is observed, and (c) the task specification is satisfiable given the capabilities described by the abstractions of the system and its environment.

show abstract

Learning in the limit with lattice-structured hypothesis spaces

Cited by 28 publications

References 26 publications

Automatic Detection of Intra-Word Code-Switching

Automatic Detection of Intra-Word Code-Switching

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

Adaptive Symbolic Control for Finite-State Transition Systems With Grammatical Inference

Contact Info

Product

Resources

About