Probabilistic learning of Turkish morphosemantics by latent syntax

Download

index.pdf

Date

2017

Author

Üstün, Ahmet

Metadata

Show full item record

Item Usage Stats

155
views

50
downloads

The language processing capability of humans is highly dependent on the transparent interface between syntax and semantics which is formalized as the grammar. Morphology also interferes with this interface, in languages having rich morphology such as Turkish. This thesis aims to discover word semantics in Turkish from the compositional morphosemantics by underlying latent syntax. A computational model has been developed to learn a morpheme lexicon in which each morpheme contains semantic information in logical form with a basic syntactic type. A knowledge-free segmentation algorithm based on distributional properties of words is used to extract pseudo-morphemes from words. We utilize a classical probabilistic CCG grammar for lexical learning. Since derivational changes can be handled with lexicalization of words, we employ our model for the inflectional morphemes in Turkish. The model has been tested and results obtained is reported in the thesis with various aspects.

Subject Keywords

Computational linguistics., Turkish language

URI

http://etd.lib.metu.edu.tr/upload/12621487/index.pdf
https://hdl.handle.net/11511/26771

Collections

Graduate School of Informatics, Thesis

Suggestions

OpenMETU
Core

An examination of quantifier scope ambiguity in Turkish Kurt, Kürşad; Bozşahin, Hüseyin Cem; Department of Cognitive Sciences (2006) This study investigates the problem of quantifier scope ambiguity in natural languages and the various ways with which it has been accounted for, some of which are problematic for monotonic theories of grammar like Combinatory Categorial Grammar (CCG) which strive for solutions that avoid non-monotonic functional application, and assume complete transparency between the syntax and the semantics interface of a language. Another purpose of this thesis is to explore these proposals on examples from Turkish and...
Prediction of words in Turkish sentences by LSTM-based language modeling Algan, Abdullah Can; Acartürk, Cengiz; Çöltekin, Çağrı; Department of Cognitive Sciences (2021-3-29) Language comprehension is affected by predictions because it is an incremental process. Predictability has been an important aspect of studying language processing and acquisition in cognitive science. In parallel, Natural Language Processing field takes advantage of advanced technology to teach computers how to understand natural language. Our study investigates if there is an alignment between human predictability and artificial language model predictability results. This thesis solely focuses on the Turk...
Enriching ebXML registries with OWL ontologies for efficient service discovery Doğaç, Asuman; Kabak, Y; Laleci, GB (2004-03-29) Web services, like their real life counterparts have several properties and thus truly useful semantic information can only be defined through standard ontology languages. Semantic Web is an important initiative in this respect. However although service registries are the major mechanisms to discover services, the semantic support provided by service registries is completely detached from the Semantic Web effort.
Metapragmatics of (im)politeness in Turkish: an exploratory emic investigation Güler Işık, Hale; Ruhi, Şükriye; Department of English Language Education (2008) Adopting an eclectic analytic perspective of discourse analysis, conversation analysis and functional approaches, this study conducts an in-depth pragmatic analysis and describes the function of three pragmatic particles yani, iste and sey in casual, conversational Turkish. All three particles have multiple functions, which are described by reference to occurrences in utterances within three different domains of conversation. While utterance initial occurrences of yani are mainly connective and continuative...
Semantic dimensionality reduction during language acquisition: A window into concept representation Özcan, Rojda; Bozşahin, Hüseyin Cem; Department of Cognitive Sciences (2022-8-31) We explore the dimensionality in the semantic representations derived from the Eve fragment of the CHILDES database to gain insights into whether or not semantic dimensionality reduc- tion (DR) occurs during language acquisition, and if so to gain insights into how this reduction of dimensions could look like. We start exploring these representations that are in the form of lambda terms (LTs) by trying to find different representations for them which would be more suitable for the use of DR techniques on th...

Citation Formats

A. Üstün, “Probabilistic learning of Turkish morphosemantics by latent syntax,” M.S. - Master of Science, Middle East Technical University, 2017.