Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 17 of 17 for “"universal dependencies"”.
-
Investigating multilingual approaches for parsing universal dependencies
… We then turn to the topic of parsing Enhanced Universal Dependencies (EUD) Graphs, which are an extension of basic Universal Dependencies trees, where we describe the DCU-EPFL submission to the 2021 IWPT shared task on EUD parsing. Here, we developed a multitask model to jointly learn the tasks …
-
Η Μεσσηνιακή Διάλεκτος στο πλαίσιο των Universal Dependencies: Επισημείωση, γλωσσική ανάλυση και προσαρμογή μοντέλου
… διαλέκτου της ελληνικής γλώσσας, στο πλαίσιο των Universal Dependencies (UD). Εστίαση δίνεται στον τρόπο με τον οποίο, το Stanza, ένα εργαλείο της Υπολογιστικής Γλωσσολογίας, μπορεί να αξιοποιηθεί για την ανάλυση γλωσσικών ποικιλιών με περιορισμένη παρουσία σε υπάρχουσες δενδροτράπεζες, όπως είναι …
-
Συντακτική επισημείωση των ρηματικών πολυλεκτικών εκφράσεων της Ελληνικής στο πλαίσιο των Καθολικών Εξαρτήσεων (Universal dependencies)
… αναπαράσταση , ακολουθήθηκαν ρητά οι οδηγίες των Universal Depedencies (UDs). Μέσω αυτής της διαδικασίας, αν και δομικά είναι σταθερές, εμφανίζουν ορισμένη συντακτική ποικιλία. Για το δεύτερο στάδιο, έγινε χρήση του εργαλείου Stanza, για την αναγνώριση και την ανάλυση των ΠΛΕ. Μέσα από τη …
-
A formal specification for syntactic annotation and its usage in corpus development and maintenance: a case study in universal dependencies
… of the syntactic annotation standard Universal Dependencies, a project developed by the NLP community around the world which is growing in importance. We argue that this formal specification is useful for improving the quality of treebanks and reducing annotation costs, by enforcing …
-
Resourceful at Any Size: A Predictive Methodology Using Linguistic Corpus Metrics for Multi-Source Training in Neural Dependency Parsing
… models for low-resource languages. Projects like Universal Dependencies even make it possible to train highly multilingual models from standardized morphosyntactic labels. Multilingual (or, more generally, multi-source) training does not consistently improve modeling performance, however. With an …
-
Linguistic analysis and automatic dependency parsing of Tweets in modern Irish
… In this thesis, we present TwittIrish, the first Universal Dependencies treebank of tweets in Irish, a linguistically-informed, genre-specific dataset developed via a cycle of automatic syntactic annotation and manual correction. We use this novel resource to document and quantify the linguistic …
-
Theoretical results on a weightless neural classifier and application to computational linguistics
… e que uma configuração de parâmetros universal foi encontrada para o mWANN-Tagger. Análises e experimentos com as bases da Universal Dependencies (UD) mostram que o mWANN-Tagger tem potencial para superar os etiquetadores do estado da arte dada uma melhor representação de palavra. Esta …
-
The Role of Complexity in Structural Transfer: A Corpus Study from Turkish and Bulgarian
… corpus-based computational measures derived from Universal Dependencies treebanks. Various metrics are employed to measure, calculate, and compare complexity across multiple randomized samples. The results reveal a consistent tradeoff between lemma-to-form expansion and lexical diversity across …
-
Computational approaches to construction grammar and morphology
… project to introduce a CxG layer into the Universal Dependencies treebanks. We further develop a hybrid annotation pipeline that uses large LMs to reduce human annotation effort, therefore enabling the cost-efficient creation of corpora for very rare phenomena. Lastly, we show how highly …
-
Developing the first Cretan Treebank
… treebank) ευθυγραμμισμένης με την τυπολογία Universal Dependencies και προτείνει οδηγίες επισημείωσης για τα ειδικά χαρακτηριστικά της διαλέκτου, όπως τα ευφωνικά φαινόμενα και οι ηχηροποιήσεις. Μεθοδολογικά, η διπλωματική εργασία συνδυάζει ενεργή επισημείωση (active annotation), μεταφορά …
-
Neural Dependency Parsing of Informal Persian
… I then present the open-source Informal Persian Universal Dependency Treebank (iPerUDT), a new treebank created in this effort, and provide empirical evidence for the need of this treebank that focuses explicitly on informal language. Experimenting with two state-of-the-art parsers, I show that …
-
Dependency Syntax in the Automatic Detection of Irony and Stance
… interest of the scientific community in the Universal Dependencies (UD) project, which proposes a morphosyntactic annotation format aimed at creating a "universal" representation of the phenomena of morphology and syntax in a manifold of languages, in this work we made use of this format, …
-
Enhanced Representations and Efficient Analysis of Syntactic Dependencies Within and Beyond Tree Structures
… language texts into those formats. Enhanced Universal Dependencies format removes the tree constraint and the target structures become connected graphs. This thesis details the design of a tree-graph integrated-format parser, which serves as the basis of the winning solution at the IWPT 2021 …
-
Natural language question answering over knowledge graphs: dependency-based and hybrid approaches for Greek language applications
… schema specifications. The method leverages Universal Dependencies (UD) for syntactic analysis and automatically extracts the schema of the target knowledge graph. By combining UD parses with the extracted schema, it identifies semantically plausible paths over entities, properties, and …
-
Translationese indicators for human translation quality estimation (based on English-to-Russian translation of mass-media texts)
… We investigated (i) an extended set of Universal Dependencies-based morphosyntactic features as well as two lexical feature sets capturing (ii) collocational properties of translations, and (iii) ratios of vocabulary items in various frequency bands along with entropy scores from n-gram …
-
FINDING ANTIPATTERNS ACROSS LANGUAGES WITH ABSTRACT SYNTAX TREES
… scripts to easily find antipatterns. The second, Universal Abstract Syntax Trees (UASTs), creates a rule-based system for converting ASTs into UASTs. This makes antipatterns that are identical between two languages need only one query to be matched. Finally, this collection of antipatterns is used …
-
An automatic morphological analysis system for Indonesian
… Turkish, Arabic, Indonesian) as well as the Universal Dependencies MAS identifies the best practices in the field. From these, 15 design principles for the novel MAS were devised. This MAS consists of a morphological tagset, together with comprehensive justification of the morphological …