Researcher:
Şahin, Gözde Gül

Profile Picture
ORCID

Job Title

Faculty Member

First Name

Gözde Gül

Last Name

Şahin

Name

Name Variants

Şahin, Gözde Gül

Email Address

Birth Date

Filters

20224

Advanced Search

Filter by

Settings

Researcher Of Publications: search.filters.isAuthorOfPublication.f2803614-ffa8-4a0c-9797-8fce6ccc3955

Search Results

Now showing 1 - 4 of 4
  • Placeholder
    PublicationMetadata only
    On the rate of convergence of a classifier based on a transformer encoder
    (IEEE-Inst Electrical Electronics Engineers Inc, 2022) Gurevych, Iryna; Kohler, Michael; Department of Computer Engineering; Şahin, Gözde Gül; Faculty Member; Department of Computer Engineering; College of Engineering; 366984
    Pattern recognition based on a high-dimensional predictor is considered. A classifier is defined which is based on a Transformer encoder. The rate of convergence of the misclassification probability of the classifier towards the optimal misclassification probability is analyzed. It is shown that this classifier is able to circumvent the curse of dimensionality provided the a posteriori probability satisfies a suitable hierarchical composition model. Furthermore, the difference between the Transformer classifiers theoretically analyzed in this paper and the ones used in practice today is illustrated by means of classification problems in natural language processing.
  • Placeholder
    PublicationMetadata only
    UKP-SQUARE: an online platform for question answering research
    (Assoc Computational Linguistics-Acl, 2022) Baumgaertner, Tim; Wang, Kexin; Sachdeva, Rachneet; Eichler, Max; Geigle, Gregor; Poth, Clifton; Sterz, Hannah; Puerto, Haritz; Ribeiro, Leonardo F. R.; Pfeiffer, Jonas; Reimers, Nils; Gurevych, Iryna; Department of Computer Engineering; Şahin, Gözde Gül; Faculty Member; Department of Computer Engineering; College of Engineering; 366984
    Recent advances in NLP and information retrieval have given rise to a diverse set of question answering tasks that are of different formats (e.g., extractive, abstractive), require different model architectures (e.g., generative, discriminative), and setups (e.g., with or without retrieval). Despite having a large number of powerful, specialized QA pipelines (which we refer to as Skills) that consider a single domain, model or setup, there exists no framework where users can easily explore and compare such pipelines and can extend them according to their needs. To address this issue, we present UKP-SQUARE, an extensible online QA platform for researchers which allows users to query and analyze a large collection of modern Skills via a user-friendly web interface and integrated behavioural tests. In addition, QA researchers can develop, manage, and share their custom Skills using our microservices that support a wide range of models (Transformers, Adapters, ONNX), data-stores and retrieval techniques (e.g., sparse and dense). UKP-SQUARE is available on https://square.ukp-lab.de.(1)
  • Thumbnail Image
    PublicationOpen Access
    On the rate of convergence of a classifier based on a transformer encoder
    (Institute of Electrical and Electronics Engineers (IEEE), 2022) Gurevych, Iryna; Kohler, Michael; Department of Computer Engineering; Şahin, Gözde Gül; Faculty Member; Department of Computer Engineering; College of Engineering; 366984
    Pattern recognition based on a high-dimensional predictor is considered. A classifier is defined which is based on a Transformer encoder. The rate of convergence of the misclassification probability of the classifier towards the optimal misclassification probability is analyzed. It is shown that this classifier is able to circumvent the curse of dimensionality provided the a posteriori probability satisfies a suitable hierarchical composition model. Furthermore, the difference between the Transformer classifiers theoretically analyzed in this paper and the ones used in practice today is illustrated by means of classification problems in natural language processing.
  • Thumbnail Image
    PublicationOpen Access
    To augment or not to augment? a comparative study on text augmentation techniques for low-resource NLP
    (MIT Press, 2022) N/A; Şahin, Gözde Gül; Faculty Member; College of Engineering; 366984
    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. Although NLP has recently witnessed several new textual augmentation techniques, the field still lacks a systematic performance analysis on a diverse set of languages and sequence tagging tasks. To fill this gap, we investigate three categories of text augmentation methodologies that perform changes on the syntax (e.g., cropping sub-sentences), token (e.g., random word insertion), and character (e.g., character swapping) levels. We systematically compare the methods on part-of-speech tagging, dependency parsing, and semantic role labeling for a diverse set of language families using various models, including the architectures that rely on pretrained multilingual contextualized language models such as mBERT. Augmentation most significantly improves dependency parsing, followed by part-of-speech tagging and semantic role labeling. We find the experimented techniques to be effective on morphologically rich languages in general rather than analytic languages such as Vietnamese. Our results suggest that the augmentation techniques can further improve over strong baselines based on mBERT, especially for dependency parsing. We identify the character-level methods as the most consistent performers, while synonym replacement and syntactic augmenters provide inconsistent improvements. Finally, we discuss that the results most heavily depend on the task, language pair (e.g., syntactic-level techniques mostly benefit higher-level tasks and morphologically richer languages), and model type (e.g., token-level augmentation provides significant improvements for BPE, while character-level ones give generally higher scores for char and mBERT based models).