paper-with-me

Papers

Automated question generation and question answering from Turkish texts

2021-11-11 · Fatih Cagatay Akyon, Devrim Cavusoglu, Cemil Cengiz, Sinan Onur Altinuc, Alptekin Temizel

While exam-style questions are a fundamental educational tool serving a variety of purposes, manual construction of questions is a complex process that requires training, experience and resources. Automatic question generation (QG) techniques can be utilized to satisfy the need for a continuous supply of new questions by streamlining their generation. However, compared to automatic question answering (QA), QG is a more challenging task. In this work, we fine-tune a multilingual T5 (mT5) transformer in a multi-task setting for QA, QG and answer extraction tasks using Turkish QA datasets. To the best of our knowledge, this is the first academic work that performs automated text-to-text question generation from Turkish texts. Experimental evaluations show that the proposed multi-task setting achieves state-of-the-art Turkish question answering and question generation performance on TQuADv1, TQuADv2 datasets and XQuAD Turkish split. The source code and the pre-trained models are available at https://github.com/obss/turkish-question-generation.

📄 PDF Abstract BibTeX arXiv:2111.06476

Code (1)

obss/turkish-question-generation 공식 구현 pytorch

Tasks

Question AnsweringQuestion GenerationQuestion-Generation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adafactor Adafactor is a stochastic optimization method based on Adam that reduces memory usage while retaining the empirical benefits of…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Residual Connection 설명 없음
SentencePiece 설명 없음

Similar Papers 제목 키워드 기반

Türkçe Dil Modellerinin Performans Karşılaştırması Performance Comparison of Turkish Language Models

2024-04-25 · Eren Dogan, M. Egemen Uzun, Atahan Uz, H. Emre Seyrek 외

The developments that language models have provided in fulfilling almost all kinds of tasks have attracted the attention of not only researchers but also the society and have enabled them to become products. There are co…

In-Context LearningQuestion Answering

VBART: The Turkish LLM

2024-03-02 · Meliksah Turker, Mehmet Erdi Ari, Aydin Han

We present VBART, the first Turkish sequence-to-sequence Large Language Models (LLMs) pre-trained on a large corpus from scratch. VBART are compact LLMs based on good ideas leveraged from BART and mBART models and come i…

Abstractive Text SummarizationQuestion AnsweringQuestion GenerationQuestion-Generation+2

Developing Question-Answering Models in Low-Resource Languages: A Case Study on Turkish Medical Texts Using Transformer-Based Approaches

2024-10-16 · International Artificial Intelligence and Data Processing Symposium 2024 10 · Mert Incidelen, Murat Aydogan

In this study, transformer-based pre-trained language models were fine-tuned using medical texts for question-answering (QA) tasks in Turkish, a low-resource language. Variations of the BERTurk pre-trained language model…

Language ModelingLanguage ModellingQuestion Answering

Cetvel: A Unified Benchmark for Evaluating Language Understanding, Generation and Cultural Capacity of LLMs for Turkish

2025-08-22 · Yakup Abrek Er, Ilker Kesen, Gözde Gül Şahin, Aykut Erdem arxiv

We introduce Cetvel, a comprehensive benchmark designed to evaluate large language models (LLMs) in Turkish. Existing Turkish benchmarks often lack either task diversity or culturally relevant content, or both. Cetvel ad…

Grammatical Error CorrectionMachine TranslationQuestion Answering

TurkishMMLU: Measuring Massive Multitask Language Understanding in Turkish

2024-07-17 · Arda Yüksel, Abdullatif Köksal, Lütfi Kerem Şenel, Anna Korhonen 외

Multiple choice question answering tasks evaluate the reasoning, comprehension, and mathematical abilities of Large Language Models (LLMs). While existing benchmarks employ automatic translation for multilingual evaluati…

MathMultiple-choiceQuestion Answering