Search Results for author:
Found 11 papers, 4 papers with code
D2U: Distance-to-Uniform Learning for Out-of-Scope Detection
Supervised training with cross-entropy loss implicitly forces models to produce probability distributions that follow a discrete delta distribution.
LlamaTurk: Adapting Open-Source Generative Large Language Models for Low-Resource Language
Despite advancements in English-dominant generative large language models, further development is needed for low-resource languages to enhance global accessibility.
PejorativITy: Disambiguating Pejorative Epithets to Improve Misogyny Detection in Italian Tweets
Disambiguating the meaning of such terms might help the detection of misogyny.
ARC-NLP at PAN 2023: Transition-Focused Natural Language Inference for Writing Style Detection
For the easy and medium setups, we submit transition-focused natural language inference based on DeBERTa with warmup training, and the same model without transition for the hard setup.
ARC-NLP at PAN 2023: Hierarchical Long Text Classification for Trigger Detection
In this paper, we describe our approach for the Trigger Detection shared task at PAN CLEF 2023, where we want to detect multiple triggering content in a given Fanfiction document.
ARC-NLP at Multimodal Hate Speech Event Detection 2023: Multimodal Methods Boosted by Ensemble Learning, Syntactical and Entity Features
Throughout the Russia-Ukraine war, both opposing factions heavily relied on text-embedded images as a vehicle for spreading propaganda and hate speech.
Tweets Under the Rubble: Detection of Messages Calling for Help in Earthquake Disaster
The importance of social media is again exposed in the recent tragedy of the 2023 Turkey and Syria earthquake.
Not Good Times for Lies: Misinformation Detection on the Russia-Ukraine War, COVID-19, and Refugees
Misinformation spread in online social networks is an urgent-to-solve problem having harmful consequences that threaten human health, public safety, economics, and so on.
Impact of Tokenization on Language Models: An Analysis for Turkish
Furthermore, we find that increasing the vocabulary size improves the performance of Morphological and Word-level tokenizers more than that of de facto tokenizers.
Large-Scale Hate Speech Detection with Cross-Domain Transfer
The experimental results supported by statistical tests show that Transformer-based language models outperform conventional bag-of-words and neural models by at least 5% in English and 10% in Turkish for large-scale hate speech detection.
ConQX: Semantic Expansion of Spoken Queries for Intent Detection based on Conditioned Text Generation
To provide additional information regarding the query and enhance the performance of intent detection, we propose a method for semantic expansion of spoken queries, called ConQX, which utilizes the text generation ability of an auto-regressive language model, GPT-2.
