Suzan Üsküdarlı

Büşra Marşan, Salih Furkan Akkurt, Muhammet Şen et al.

In this study, we aim to offer linguistically motivated solutions to resolve the issues of the lack of representation of null morphemes, highly productive derivational processes, and syncretic morphemes of Turkish in the BOUN Treebank without diverging from the Universal Dependencies framework. In order to tackle these issues, new annotation conventions were introduced by splitting certain lemmas and employing the MISC (miscellaneous) tab in the UD framework to denote derivation. Representational capabilities of the re-annotated treebank were tested on a LSTM-based dependency parser and an updated version of the BoAT Tool is introduced.

S. Uskudarli, E. Gökdeniz, R. Canbeyli

Online scientific publications provide vast opportunities for researchers. Alas, the quantity and the rate of increase in the articles make the utilization of these resources very challenging. This work presents as inquiry-based approach to support the articulation of complex inter-related queries to gain insights regarding how these subjects have been studied in conjunction with one another as reported in the scientific literature. For this purpose we introduce inquiries that represent inter-related subqueries that are of interest to a researcher. The inquiries are expanded to better capture the intent of the inquirer, from which several queries are generated that represent various juxtapositions of the subjects in consideration. The sets of queries are used to search repositories to yield results that reveal quantitative and temporal relations among the subjects of the inquiry. A web-based tool, NeuroBoun, is developed as a proof of concept for medical publications found in PubMed. A use case related to the asymmetry of amygdala is presented to illustrate the potentials of the proposed approach.

T. B. Dinesh, S. Uskudarli

The accessibility of content for all has been a key goal of the Web since its conception. However, true accessibility -- access to relevant content in the global context -- has been elusive for reasons that extend beyond physical accessibility issues. Among them are the spoken languages, literacy levels, expertise, and culture. These issues are highly significant, since information may not reach those who are the most in need of it. For example, the minimum wage laws that are published in legalese on government sites and the low-literate and immigrant populations. While some organizations and volunteers work on bridging such gaps by creating and disseminating alternative versions of such content, Web scale solutions much be developed to take advantage of its distributed dissemination capabilities. This work examines content accessibility from the perspective of inclusiveness. For this purpose, a human in the loop approach for renarrating Web content is proposed, where a renarrator creates an alternative narrative of some Web content with the intent of extending its reach. A renarration relates some Web content with an alternative version by means of transformations like simplification, elaboration, translation, or production of audio and video material. This work presents a model and a basic architecture for supporting renarrations along with various scenarios. We also discuss the potentials of the W3C specification for Web Annotation Data Model towards a more inclusive and decentralized social web.

Onur Güngör, Suzan Üsküdarlı, Tunga Güngör

Previous studies have shown that linguistic features of a word such as possession, genitive or other grammatical cases can be employed in word representations of a named entity recognition (NER) tagger to improve the performance for morphologically rich languages. However, these taggers require external morphological disambiguation (MD) tools to function which are hard to obtain or non-existent for many languages. In this work, we propose a model which alleviates the need for such disambiguators by jointly learning NER and MD taggers in languages for which one can provide a list of candidate morphological analyses. We show that this can be done independent of the morphological annotation schemes, which differ among languages. Our experiments employing three different model architectures that join these two tasks show that joint learning improves NER performance. Furthermore, the morphological disambiguator's performance is shown to be competitive.

A. Yıldırım, S. Uskudarli

The extensive use of social media for sharing and obtaining information has resulted in the development of topic detection models to facilitate the comprehension of the overwhelming amount of short and distributed posts. Probabilistic topic models, such as Latent Dirichlet Allocation, and matrix factorization based approaches such as Latent Semantic Analysis and Non-negative Matrix Factorization represent topics as sets of terms that are useful for many automated processes. However, the determination of what a topic is about is left as a further task. Alternatively, techniques that produce summaries are human comprehensible, but less suitable for automated processing. This work proposes an approach that utilizes Linked Open Data (LOD) resources to extract semantically represented topics from collections of microposts. The proposed approach utilizes entity linking to identify the elements of topics from microposts. The elements are related through co-occurrence graphs, which are processed to yield topics. The topics are represented using an ontology that is introduced for this purpose. A prototype of the approach is used to identify topics from 11 datasets consisting of more than one million posts collected from Twitter during various events, such as the 2016 US election debates and the death of Carrie Fisher. The characteristics of the approach with more than 5 thousand generated topics are described in detail. The potentials of semantic topics in revealing information, that is not otherwise easily observable, is demonstrated with semantic queries of various complexities. A human evaluation of topics from 36 randomly selected intervals resulted in a precision of 81.0% and F1 score of 93.3%. Furthermore, they are compared with topics generated from the same datasets from an approach that produces human readable topics from microblog post collections.

Onur Gungor, Eray Yildiz, Suzan Uskudarli et al.

In this work, we present new state-of-the-art results of 93.59,% and 79.59,% for Turkish and Czech named entity recognition based on the model of (Lample et al., 2016). We contribute by proposing several schemes for representing the morphological analysis of a word in the context of named entity recognition. We show that a concatenation of this representation with the word and character embeddings improves the performance. The effect of these representation schemes on the tagging performance is also investigated.