Experiments on automatic prosodic labeling
- Antje Schweitzer
This paper presents results from experiments on automatic prosodic labeling. Using the WEKA machine learning soft-ware , classifiers were trained to determine for each syllable in a speech database of a male speaker its pitch accent and its boundary tone. Pitch accents and boundaries are according to the GToBI(S) dialect, with slight modifications. Classification was based on 35 attributes involving PaIntE F0 parametrization  and normalized phone durations, but also some phonologi-cal information as well as higher-linguistic information. Several classification algorithms yield results of approx. 78 % accuracy on the word level for pitch accents, and approx. 88 % accuracy...
- Nikhil Sudhakar Joshi; Nikhil Sudhakar Joshi
A semantics-first approach for word learning using visuo-linguistic corpus by
Development of English Speech Database Spoken by Japanese Learners
Due to recent advances in speech processing tech-niques, we can see a various kinds of practical speech applications in both laboratories and the real world. One of the major applications in Japan is CALL (computer assisted language learning) systems. It is well-known that most of the recent speech tech-nologies are based upon statistical methods, which require a large amount of speech data. While we can find lots of speech corpora available from distribution sites such as Linguistic Data Consortium and Eu-ropean Language Resources Association, the num-ber of speech corpora built especially for CALL sys-tem development is strongly restricted. In this...
A graph-based approach for implicit discourse relations
- Yannick Versley
Recognizing and classifying implicit discourse relations is a challenging task since hardly any strong indicators exist, and a variety of weak indicators has to be harnessed to yield evidence for a particular discourse relation or another. Most current approaches rely on a combination of shallow, surface-based features and rather specialized hand-crafted features, with a considerable gap in between which is partly due to the sheer complexity of combining evidence from different levels of linguistic description. As a way to avoid both the shallowness of word-based representations and the lack of coverage of specialized linguistic features, we use a graph-based representation...
Automatic estimation of one’s age with his/her speech based upon acoustic modeling techniques of speakers
- Nobuaki Minematsu; Mariko Sekiguchi; Keikichi Hirose
This paper proposes a technique which automatically estimates speakers ’ age only with acoustic, not linguistic, information of their utterances. This method is based upon speaker recognition techniques. In the current work, we firstly divided speakers of two databases, JNAS and S(senior)-JNAS, into two groups by listening tests. One group has only the speakers whose speech sounds so aged that one should take special care when he/she talks to them. The other group has the remaining speakers of the two databases. After that, each speaker group was modeled with GMM. Experi-ments of automatic identification of elderly speakers showed the correct...
- Ingo Eduard Isphording; Short Summary; Ingo Eduard Isphording; Continentale Sachversicherung Ag
Ingo Isphording currently works as a Research Associate at IZA Bonn. He obtained his PhD at the Chair “Economic Policy: Competition Theory and Policy ” of Prof. Dr. John P. Haisken-DeNew at the Ruhr University Bochum in May 2013. He obtained a Bachelor degree in "Economics and Social Psychology " from the Ruhr University Bochum in 2007 and a Master of Arts in "Economics " from University of Duisburg-Essen, Germany in 2009. He spent one exchange semester at the Norwegian School of Business and Economics in Bergen, Norway in 2008. His main fields of interest are applied migration economics, especially...
From Existential Graphs to Conceptual Graphs
- John F. Sowa
Abstract. Existential graphs (EGs) are a simple, readable, and expressive graphic notation for logic. Conceptual graphs (CGs) combine a logical foundation based on EGs with features of the semantic networks used in artificial intelligence and computational linguistics. CG design principles address logical, linguistic, and cognitive requirements: a formal semantics defined by the ISO standard for Common Logic; the flexibility to support the expressiveness, context dependencies, and metalevel commentary of natural language; and cognitively realistic operations for reasoning by induction, deduction, abduction, and analogy. To accommodate the vagueness and ambiguities of natural language, informal heuristics can supplement the formal semantics. With...
Princeton/Stanford Working Papers in Classics The Riddle of the sp(h)ij-: The Greek Sphinx and her Indic and Indo-European Background
- Joshua T. Katz
Abstract: The name of the Sphinx, the Greek female monster who had fun killing passers-by who could not answer her riddle, has long been an etymological conundrum. On the basis of literary, linguistic, and anthropological evidence from, above all, Greece and India, this paper comes to a novel understanding of the Sphinx ’ origin, concluding that her oldest moniker, (S)F∞k-, is related to a newly uncovered Greek noun f€ki ˚ ‘buttocks ’ and to a Sanskrit word for the same body part, sphij-, a hitherto misunderstood form of which appears, in turn, in a riddle in the oldest Indic text,...
From Linguistic Diversity to Plurilingual Education Reference Study
- Tove Skutnabb-kangas
All correspondence concerning this publication or the reproduction or
ed. by V. Koseska-Toszewa, L. Dimitrova and R. Roszko, SOW Publishing House Interactive Discovery of Ontological Knowledge for Modelling Language Resources
- André Wlodarczyk
Computer-aided Acquisition of Semantic Knowledge (CASK) is aimed at describing a number of semantic fields of a few European languages using data mining techniques elaborated within the framework of the new paradigm of computation known as Knowledge Discovery in Databases (KDD). CASK's motivation is to dig deeper in order to find building blocks which could be used in various sophisticated ways. The project is interdisciplinary involving scientific cooperation of experts in linguistics with information engineers. The task of linguists consists in an interactive (computer-aided) discovery of ontology-based definitions of feature structures using the SEMANA (Semantic Analyser) software which was designed...
Living with a Tabletop: Analysis and Observations of Long Term Office Use of a MultiTouch Table
- Daniel Wigdor; Gerald Penn; Kathy Ryall; Alan Esenther; Chia Shen
Multi-touch tabletops have been the focus of significant recent study but, to date, few devices have moved from prototype to installed use. In this paper, we present observation and analysis of a subject who has used a direct-touch tabletop as his primary computing environment for the past 13 months, driving all manner of applications in a standard MS Windows environment. We present the results of three research instruments: a structured interview with the user, an analysis of touch and click locations when operating in desktop and tabletop modes over several days, and linguistic analysis of email composition over several months....
THE CONSEQUENCES OF DEMOGRAPHIC TRENDS FOR LANGUAGE LEARNING AND DIVERSITY Guide for the Development of Language Education Policies in Europe From Linguistic Diversity to Plurilingual Education Reference Study
- Pádraig Ó Riagáin
The opinions expressed in this work are those of the author and do not necessarily reflect the official policy of the Council of Europe. All correspondence concerning this publication or the reproduction or translation of all or part of the document should be addressed to the Director
7 A Fuzzy Logic Based Software Cost Estimation Model
- Shahid Kamal; Jamal Abdul Nasir
Software cost estimation is a challenging and onerous task. Estimation by analogy is one of the expedient techniques in software effort estimation field. However, the methodology utilized for the estimation of software effort by analogy is not able to handle the categorical data in an explicit and precise manner. Early software estimation models are based on regression analysis or mathematical derivations. Today’s models are based on simulation, neural network, genetic algorithm, soft computing, fuzzy logic modelling etc. This paper aims to utilize a fuzzy logic model to improve the accuracy of software effort estimation. In this approach fuzzy logic is...
A paradigm for non-head-driven parsing: Parameterized message-passing
- Bonnie Dorr; Jye-hoon Lee; Dekang Lin; Sungki Suh
The parsing component of previous principle-based parsers are inecient since they tend to adopt a generate-and-test paradigm. We com-bine the benets of a message-passing paradigm with the benets of a parametric approach in the implementation of a parser that avoids overgener-ation and is easily ported to multiple languages. The algorithm has been implemented in C++ and successfully tested on well-known, translationally divergent sentences. We are currently incorporat-ing the parser into a machine translation (MT) system called PRINCITRAN.
Metaphysical Semantics Meets Multiple Realizability
- Jonathan Schaffer
Sider’s Writing the Book of the World is an outstanding work. In an earlier review (Schaffer forthcoming) I called it ‘masterful ’ and ‘required reading’, while worrying about Sider’s notion(s) of structure. Here I offer the further praise of further discussion, centred on a separate worry concerning whether Sider’s metaphysical semantics can handle multiple realizability. Metaphysical semantics is supposed to connect the non-fundamental to the fundamental in a distinctively linguistic way, explaining how non-fundamen-tal truths can be grounded in fundamental facts, and so inducing a radically eliminative vision of the non-fundamental as mere talk. I wonder how the story goes...
Origin of symbol-using systems: speech, but not sign, without the semantic urge
- Martin Sereno
Natural language-- both spoken and signed-- is a multichannel phenomenon, involving facial and body expression, and voice and visual intonation that is often used in the service of a social urge to communicate meaning. Given that iconicity seems easier and less abstract than making arbitrary connections between sound and meaning, iconicity has often been invoked in the origin of language alongside the urge to convey meaning. To get a fresh perspective, we critically distinguish the origin of a system capable of evolution from the subsequent evolution that system becomes capable of. Human language arose on a substrate of a system...
1 Cognition and language: from apprehension to judgment – Quantum
- F. T. Arecchi
We critically discuss the two moments of human cognition, namely, apprehension (A),whereby a coherent perception emerges from the recruitment of neuronal groups, and judgment(B),that entails the comparison of two apprehensions acquired at different times, coded in a suitable language and recalled by memory. (B) requires self-consciousness, in so far as the agent who expresses the judgment must be aware that the two apprehensions are submitted to his/her own scrutiny and that it is his/her duty to extract a mutual relation. Since (B) lasts around 3 seconds, the semantic value of the pieces under comparison must be decided within this time....
Learning Verb Classes in an Incremental Model
- Libby Barak; Afsaneh Fazly; Suzanne Stevenson
The ability of children to generalize over the linguistic input they receive is key to acquiring productive knowledge of verbs. Such generalizations help children extend their learned knowledge of constructions to a novel verb, and use it appropriately in syntactic patterns previously unobserved for that verb—a key factor in language productivity. Computational models can help shed light on the gradual development of more abstract knowledge during verb acquisition. We present an incremental Bayesian model that simultaneously and incrementally learns argument structure constructions and verb classes given nat-uralistic language input. We show how the distributional properties in the input lan-guage influence...
Sub-structure-based estimation of pronunciation proficiency and classification of learners
- Masayuki Suzuki; Nobuaki Minematsu; Dean Luo; Keikichi Hirose
Abstract—Automatic estimation of pronunciation proficiency has its specific difficulty. Adequacy in controlling the vocal organs can be estimated from spectral envelopes of input utterances but the envelope patterns are also affected easily by different speakers. To develop a pedagogically sound method for automatic estimation, the envelope changes caused by linguistic factors and those by extra-linguistic factors should be properly separated. For this aim, in our previous study , we proposed a mathematically-guaranteed and linguistically-valid speaker-invariant representa-tion of pronunciation, called speech structure. After the proposal, we have examined that representation also for ASR , ,  and, through these works, we...
Analysing Pattern for Chromium Bug Area Classification
- Trasha Gupta; Monika Gupta; Deen Dayal; Upadhyaya College
in software engineering is the modification of a software product after delivery to correct faults, to improve performance or other attributes. The purpose is to preserve the value of software over the time. The users report the bugs in the issue tracking system. Bug report contains many fields like title, description, version, OS, area etc. The quality of bug report affects the repair time. It is noticed that users often assign incorrect or don’t assign the area of bug which lead to bug reassignment and hence delay. Document categorization (based on text) with its diversified application has been widely studied...