Gözde Gül Şahin
Biographic Data
| ID | 6536310 |
|---|---|
| NAME | Gözde Gül Şahin |
| GIVEN NAMES | Gözde Gül |
| FAMILY NAME | Şahin |
| SIGNATURE | ŞAHIN G G |
| AFFILIATIONS | KUIS AI Lab, Koç University, Istanbul, Türkiye. https://gglab-ku.github.io/ |
| ORCID | 0000-0002-0332-1657 |
| VERIFIED | Yes |
| TOTAL WORKS | 3 |
| TOTAL CITATIONS | 0 |
| WORKS AS AUTHOR | 3 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 2020 |
| LATEST PUBLICATION YEAR | 2026 |
| H-INDEX | 0 |
Instructional Text Across Disciplines
Recent advances in large language models have demonstrated promising capabilities in following simple instructions through instruction tuning. However, real-world tasks often involve complex, multi-step instructions that remain challenging for current NLP systems. Robust understanding of such instructions is essential for deploying LLMs as general-purpose agents that can be programmed in natural language to perform complex, real-world tasks acros…
To Augment or Not to Augment? A Comparative Study on Text Augmentation Techniques for Low-Resource NLP
Data-hungry deep neural networks have established themselves as the de facto standard for many NLP tasks, including the traditional sequence tagging ones. Despite their state-of-the-art performance on high-resource languages, they still fall behind their statistical counterparts in low-resource scenarios. One methodology to counterattack this problem is text augmentation, that is, generating new synthetic training data points from existing data. …
Linspector
Despite an ever-growing number of word representation models introduced for a large number of languages, there is a lack of a standardized technique to provide insights into what is captured by these models. Such insights would help the community to get an estimate of the downstream task performance, as well as to design more informed neural architectures, while avoiding extensive experimentation that requires substantial computational resources …
No prominent works on this page.
Linspector
Despite an ever-growing number of word representation models introduced for a large number of languages, there is a lack of a standardized technique to provide insights into what is captured by these models. Such insights would help the community to get an estimate of the downstream task performance, as well as to design more informed neural architectures, while avoiding extensive experimentation that requires substantial computational resources …
To Augment or Not to Augment? A Comparative Study on Text Augmentation Techniques for Low-Resource NLP
Data-hungry deep neural networks have established themselves as the de facto standard for many NLP tasks, including the traditional sequence tagging ones. Despite their state-of-the-art performance on high-resource languages, they still fall behind their statistical counterparts in low-resource scenarios. One methodology to counterattack this problem is text augmentation, that is, generating new synthetic training data points from existing data. …
Instructional Text Across Disciplines
Recent advances in large language models have demonstrated promising capabilities in following simple instructions through instruction tuning. However, real-world tasks often involve complex, multi-step instructions that remain challenging for current NLP systems. Robust understanding of such instructions is essential for deploying LLMs as general-purpose agents that can be programmed in natural language to perform complex, real-world tasks acros…
Topic Modeling (3 works) · Artificial Intelligence (2 works) · Computer Science (2 works) · Linguistics (2 works) · Multimodal Machine Learning Applications (2 works) · Natural language processing (2 works) · Natural Language Processing Techniques (2 works) · Set (abstract data type (2 works) · Text Readability and Simplification (2 works) · Augment (1 work)