Tolga Uslu


2018

pdf bib
LTV: Labeled Topic Vector
Daniel Baumartz | Tolga Uslu | Alexander Mehler
Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations

In this paper we present LTV, a website and API that generates labeled topic classifications based on the Dewey Decimal Classification (DDC), an international standard for topic classification in libraries. We introduce nnDDC, a largely language-independent natural network-based classifier for DDC, which we optimized using a wide range of linguistic features to achieve an F-score of 87.4%. To show that our approach is language-independent, we evaluate nnDDC using up to 40 different languages. We derive a topic model based on nnDDC, which generates probability distributions over semantic units for any input on sense-, word- and text-level. Unlike related approaches, however, these probabilities are estimated by means of nnDDC so that each dimension of the resulting vector representation is uniquely labeled by a DDC class. In this way, we introduce a neural network-based Classifier-Induced Semantic Space (nnCISS).

pdf bib
FastSense: An Efficient Word Sense Disambiguation Classifier
Tolga Uslu | Alexander Mehler | Daniel Baumartz | Wahed Hemati
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

2017

pdf bib
TextImager as a Generic Interface to R
Tolga Uslu | Wahed Hemati | Alexander Mehler | Daniel Baumartz
Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics

R is a very powerful framework for statistical modeling. Thus, it is of high importance to integrate R with state-of-the-art tools in NLP. In this paper, we present the functionality and architecture of such an integration by means of TextImager. We use the OpenCPU API to integrate R based on our own R-Server. This allows for communicating with R-packages and combining them with TextImager’s NLP-components.

2016

pdf bib
Text2voronoi: An Image-driven Approach to Differential Diagnosis
Alexander Mehler | Tolga Uslu | Wahed Hemati
Proceedings of the 5th Workshop on Vision and Language

pdf bib
TextImager: a Distributed UIMA-based System for NLP
Wahed Hemati | Tolga Uslu | Alexander Mehler
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations

More and more disciplines require NLP tools for performing automatic text analyses on various levels of linguistic resolution. However, the usage of established NLP frameworks is often hampered for several reasons: in most cases, they require basic to sophisticated programming skills, interfere with interoperability due to using non-standard I/O-formats and often lack tools for visualizing computational results. This makes it difficult especially for humanities scholars to use such frameworks. In order to cope with these challenges, we present TextImager, a UIMA-based framework that offers a range of NLP and visualization tools by means of a user-friendly GUI. Using TextImager requires no programming skills.