paper-with-me

홈 › Papers

A Modern Turkish Poet: Fine-Tuned GPT-2

2023-09-15 · 8th International Conference on Computer Science and Engineering (UBMK) 2023 9 · Uygar Kurt, Aykut Çayır

Generative tasks are getting more realistic thanks to the improvements in deep learning. Text generation is getting increasingly important as LLMs (large language models) get more advanced. Even though ChatGPT gave rise to many computer-generated literary works, it has several limitations, such as not being open-sourced and can't be fine-tuned. Because other LLMs are understudied in Turkish, they usually can't be used efficiently to generate literary work. In this paper, we fine-tuned GPT-2 [1] models on sixty Turkish poem categories and trained five models that convey different emotions and write on different topics. The results are gathered in a 70-page Turkish poem book named “Gerçekligin İçinde” that contains 50 poems in total, 10 poems for each chapter. The book got published by Amazon [2], Goodreads [3] and Google Books [4].

📄 PDF Abstract BibTeX

Code (1)

uygarkurt/A-Modern-Turkish-Poet-Fine-Tuned-GPT-2

Tasks

Text Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Attention 설명 없음
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Modern French Poetry Generation with RoBERTa and GPT-2

2022-12-06 · Mika Hämäläinen, Khalid Alnajjar, Thierry Poibeau

We present a novel neural model for modern poetry generation in French. The model consists of two pretrained neural models that are fine-tuned for the poem generation task. The encoder of the model is a RoBERTa based one…

DecoderNatural Language UnderstandingText Generation

KPoEM: A Human-Annotated Dataset for Emotion Classification and RAG-Based Poetry Generation in Korean Modern Poetry

2025-09-04 · Iro Lim, Haein Ji, Byungjun Kim arxiv

This study introduces KPoEM (Korean Poetry Emotion Mapping), a novel dataset that serves as a foundation for both emotion-centered analysis and generative applications in modern Korean poetry. Despite advancements in NLP…

Emotion Classification

Instruction-Guided Poetry Generation in Arabic and Its Dialects

2026-04-30 · Abdelrahman Sadallah, Kareem Elozeiri, Mervat Abassy, Rania Elbadry 외 arxiv

Poetry has long been a central art form for Arabic speakers, serving as a powerful medium of expression and cultural identity. While modern Arabic speakers continue to value poetry, existing research on Arabic poetry wit…

BIRDTurk: Adaptation of the BIRD Text-to-SQL Dataset to Turkish

2026-02-03 · Burak Aktaş, Mehmet Can Baytekin, Süha Kağan Köse, Ömer İlbilgi 외 arxiv

Text-to-SQL systems have achieved strong performance on English benchmarks, yet their behavior in morphologically rich, low-resource languages remains largely unexplored. We introduce BIRDTurk, the first Turkish adaptati…

Can ChatGPT Really Understand Modern Chinese Poetry?

2026-03-21 · Shanshan Wang, Derek F. Wong, Jingming Yao, Lidia S. Chao arxiv

ChatGPT has demonstrated remarkable capabilities on both poetry generation and translation, yet its ability to truly understand poetry remains unexplored. Previous poetry-related work merely analyzed experimental outcome…