Papers by Arzucan Özgür

11 papers
Dealing with Data Scarcity in Spoken Question Answering (2024.lrec-main)

Copied to clipboard

Challenge: erroneous automatic speech recognition transcriptions and data scarcity hinder spoken QA models . paper focuses on using limited annotated data to improve spoken qa performance .
Approach: They propose a framework for utilizing limited annotated data effectively to improve spoken QA performance.
Outcome: The proposed model produces question-answer pairs from unannotated data with 5.5% relative gain over the model trained with annotated datasets.
Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution (2021.emnlp-main)

Copied to clipboard

Challenge: Multi-label text classification is a challenging task because it requires capturing label dependencies.
Approach: They propose to use distribution-balanced loss functions to solve label dependency problems in multi-label text classification by capturing label dependencies from a fixed-set of labels.
Outcome: The proposed loss function addresses both the class imbalance and label linkage problems and outperforms other loss functions.
BOUN-ISIK Participation: An Unsupervised Approach for the Named Entity Normalization and Relation Extraction of Bacteria Biotopes (D19-57)

Copied to clipboard

Challenge: In 2011, the Bacteria Biotope Task was conducted for the first time as a part of the BioNLP Shared Task targeting the extraction of useful information regarding bacteria and their habitats.
Approach: They propose two systems for the normalization of entities and the identification of relations between entities given a biomedical text.
Outcome: The proposed method performs as good as deep learning based methods which require labeled data.
Evaluating the Quality of a Corpus Annotation Scheme Using Pretrained Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Pretrained language models and large language models are increasingly used to assist in a variety of natural language processing tasks.
Approach: They propose to use pretrained language models and large language models to evaluate their quality in natural language processing.
Outcome: The proposed annotation scheme (2.11) yields sentences with higher success rate than the previous one.
HATECAT-TR: A Hate Speech Span Detection and Categorization Dataset for Turkish (2025.findings-emnlp)

Copied to clipboard

Challenge: a new dataset of Turkish tweets contains 4465 hateful spans . each hateful post is directed at one of eight minority groups .
Approach: They propose a span-annotated dataset of Turkish tweets containing 4465 hateful spans . each hateful spat is categorized into one of five discourse types .
Outcome: The proposed dataset contains 4465 hateful spans across 2981 tweets . each span is categorized into one of five discourse types .
A Dataset and BERT-based Models for Targeted Sentiment Analysis on Turkish Texts (2022.acl-srw)

Copied to clipboard

Challenge: Sentiment analysis is a field that is growing due to the availability of the Internet and the growing number of online platforms.
Approach: They propose an annotated Turkish dataset suitable for targeted sentiment analysis.
Outcome: The proposed models outperform the traditional models for the targeted sentiment analysis task.
TULAP - An Accessible and Sustainable Platform for Turkish Natural Language Processing Resources (2023.eacl-demo)

Copied to clipboard

Challenge: a growing interest in the field of natural language processing is resulting in applications solving NLP tasks.
Approach: They propose to create an open-source platform to share Turkish NLP resources . they propose to use the platform to publish open-sourced Turkish Nlp resources based on a research lab's datasets and tools.
Outcome: The proposed platform is easy-to-use and publishes open-source Turkish NLP resources.
Improving Code-Switching Dependency Parsing with Semi-Supervised Auxiliary Tasks (2022.findings-naacl)

Copied to clipboard

Challenge: Code-switching dependency parsing is a challenging task due to the scarcity of necessary resources and structural difficulties embedded in code-switch languages.
Approach: They propose to use sequence labeling models as auxiliary tasks for code-switched dependency parsing in a semi-supervised scheme and acquire state-of-the-art scores on all studied languages.
Outcome: The proposed model outperforms the previous model by 7.4 LAS points on average on all of the studied languages.
A Framework for Automatic Generation of Spoken Question-Answering Data (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing frameworks to automatically generate a spoken question answering dataset are limited by the amount of spoken text documents available.
Approach: They propose to use QG module to generate questions from text documents, TTS module to convert text documents into spoken form and automatic speech recognition module to transcribe spoken content.
Outcome: The proposed framework is efficient for automatically generating spoken QA datasets.
The RELX Dataset and Matching the Multilingual Blanks for Cross-Lingual Relation Classification (2020.findings-emnlp)

Copied to clipboard

Challenge: Current approaches for relation classification are focused on the English language and require lots of training data with human annotations.
Approach: They propose a baseline model based on Multilingual BERT and a new multilingual pretraining setup . they propose 'relationship classification' models that use distant supervision .
Outcome: The proposed model significantly improves the baseline model with distant supervision.
A Dataset for Investigating the Impact of Context for Offensive Language Detection in Tweets (2023.findings-emnlp)

Copied to clipboard

Challenge: Offensive language detection is crucial in natural language processing . we investigated the importance of contextual information for detecting offensive language in tweets .
Approach: They investigated the importance of contextual information for detecting offensive language in tweets . they used a Turkish tweet dataset with over 28,000 tweet-reply pairs .
Outcome: The proposed model performs better with and without contextual information than with and with contextual information.

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