Search Results for author: Tunga Güngör

Found 14 papers, 4 papers with code

Dictionary-Based Concept Mining: An Application for Turkish

no code implementations12 Jan 2014 Cem Rıfkı Aydın, Ali Erkan, Tunga Güngör, Hidayet Takçı

In this study, a dictionary-based method is used to extract expressive concepts from documents.

Improving Named Entity Recognition by Jointly Learning to Disambiguate Morphological Tags

1 code implementation17 Jul 2018 Onur Güngör, Suzan Üsküdarlı, Tunga Güngör

In this work, we propose a model which alleviates the need for such disambiguators by jointly learning NER and MD taggers in languages for which one can provide a list of candidate morphological analyses.

Morphological Disambiguation named-entity-recognition +2

Generating Word and Document Embeddings for Sentiment Analysis

no code implementations5 Jan 2020 Cem Rıfkı Aydın, Tunga Güngör, Ali Erkan

In this paper, we combine contextual and supervised information with the general semantic representations of words occurring in the dictionary.

Sentiment Analysis

A Hybrid Approach to Dependency Parsing: Combining Rules and Morphology with Deep Learning

no code implementations24 Feb 2020 Şaziye Betül Özateş, Arzucan Özgür, Tunga Güngör, Balkız Öztürk

Our first approach combines a state-of-the-art deep learning-based parser with a rule-based approach and the second one incorporates morphological information into the parser.

Dependency Parsing Morphological Analysis

Hierarchical Multi Task Learning with Subword Contextual Embeddings for Languages with Rich Morphology

no code implementations25 Apr 2020 Arda Akdemir, Tetsuo Shibuya, Tunga Güngör

In this study, we propose using subword contextual embeddings to capture the morphological information for languages with rich morphology.

Dependency Parsing Multi-Task Learning +3

Enhancements to the BOUN Treebank Reflecting the Agglutinative Nature of Turkish

no code implementations24 Jul 2022 Büşra Marşan, Salih Furkan Akkurt, Muhammet Şen, Merve Gürbüz, Onur Güngör, Şaziye Betül Özateş, Suzan Üsküdarlı, Arzucan Özgür, Tunga Güngör, Balkız Öztürk

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, and syncretic morphemes of Turkish in the BOUN Treebank without diverging from the Universal Dependencies framework.

Miscellaneous

Building Efficient and Effective OpenQA Systems for Low-Resource Languages

1 code implementation7 Jan 2024 Emrah Budur, Rıza Özçelik, Dilara Soylu, Omar Khattab, Tunga Güngör, Christopher Potts

We present SQuAD-TR, a machine translation of SQuAD2. 0, and we build our OpenQA system by adapting ColBERT-QA for Turkish.

Machine Translation Question Answering

ERMI at PARSEME Shared Task 2020: Embedding-Rich Multiword Expression Identification

no code implementations COLING (MWE) 2020 Zeynep Yirmibeşoğlu, Tunga Güngör

This paper describes the ERMI system submitted to the closed track of the PARSEME shared task 2020 on automatic identification of verbal multiword expressions (VMWEs).

POS TAG

Overcoming the challenges in morphological annotation of Turkish in universal dependencies framework

no code implementations EMNLP (LAW, DMR) 2021 Talha Bedir, Karahan Şahin, Onur Gungor, Suzan Uskudarli, Arzucan Özgür, Tunga Güngör, Balkiz Ozturk Basaran

This paper presents these issues and our proposals to more accurately represent morphosyntactic information for Turkish while adhering to guidelines of UD.

Cannot find the paper you are looking for? You can Submit a new open access paper.