Papers by Olcay Taner Yıldız

4 papers
A Learning-Based Dependency to Constituency Conversion Algorithm for the Turkish Language (2022.lrec-1)

Copied to clipboard

Challenge: a team of linguists manually annotated a set of constituency trees.
Approach: They propose to create the first Turkish-based dependency-to-constituency conversion algorithm using a morphologic analyser and feature-based machine learning model.
Outcome: The proposed algorithm can be used to generate new constituency treebanks and training data for NLP resources like constituency parsers.
TRopBank: Turkish PropBank V2.0 (2020.lrec-1)

Copied to clipboard

Challenge: PropBank is a hand-annotated corpus of propositions used to obtain predicate-argument information of a language.
Approach: They present TRopBank "Turkish PropBank v2.0" which is a hand-annotated corpus of propositions . it is used to obtain the predicate-argument information of a language .
Outcome: The proposed annotations provide the predicate-argument information of a language . the proposed annotation is based on the annotations of 17.673 verbs in Turkish .
AnlamVer: Semantic Model Evaluation Dataset for Turkish - Word Similarity and Relatedness (C18-1)

Copied to clipboard

Challenge: a dataset for semantic model evaluation for Turkish is not available for the language . a similarity and relatedness evaluation resource is needed for higher level tasks .
Approach: They propose a semantic model evaluation dataset for Turkish that evaluates word similarity and word relatedness tasks while discriminating those two relations from each other.
Outcome: The proposed dataset is designed to evaluate word similarity and word relatedness tasks in Turkish.
FrameForm: An Open-source Annotation Interface for FrameNet (2021.eacl-demos)

Copied to clipboard

Challenge: FrameNet is a computational lexicography tool that provides in-depth semantic information regarding the argument structure and thematic relations of a predicate.
Approach: They introduce an open-source annotation tool that can be easily modified to accommodate predicate annotations based on Frame Semantics.
Outcome: The proposed tool can be easily modified to answer the annotation needs of a wide range of languages.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations