20 citations · 59 across the 9 of their papers we have counts for
11 papers
A Comprehensive Analysis of Static Word Embeddings for Turkish
Karahan Sarıtaş, Cahid Arda Öz, Tunga Güngör
Word embeddings are fixed-length, dense and distributed word representations that are used in natural language processing (NLP) applications. There are basically two types of word…
Incorporating Human Translator Style into English-Turkish Literary Machine Translation
Zeynep Yirmibeşoğlu, Olgun Dursun, Harun Dallı +4
Although machine translation systems are mostly designed to serve in the general domain, there is a growing tendency to adapt these systems to other domains like literary translati…
Enhancements to the BOUN Treebank Reflecting the Agglutinative Nature of Turkish
Büşra Marşan, Salih Furkan Akkurt, Muhammet Şen +7
In this study, we aim to offer linguistically motivated solutions to resolve the issues of the lack of representation of null morphemes, highly productive derivational processes, a…
Hierarchical Multitask Learning Approach for BERT
Çağla Aksoy, Alper Ahmetoğlu, Tunga Güngör
Recent works show that learning contextualized embeddings for words is beneficial for downstream tasks. BERT is one successful example of this approach. It learns embeddings by sol…
Data and Representation for Turkish Natural Language Inference
Emrah Budur, Rıza Özçelik, Tunga Güngör +1
Large annotated datasets in NLP are overwhelmingly in English. This is an obstacle to progress in other languages. Unfortunately, obtaining new annotated resources for each task in…
A Hybrid Approach to Dependency Parsing: Combining Rules and Morphology with Deep Learning
Şaziye Betül Özateş, Arzucan Özgür, Tunga Güngör +1
Fully data-driven, deep learning-based models are usually designed as language-independent and have been shown to be successful for many natural language processing tasks. However,…