no code implementations • ACL (mmsr, IWCS) 2021 • Nikolai Ilinykh, Simon Dobnik
In this paper, we examine masked self-attention in a multi-modal transformer trained for the task of image captioning.
1 code implementation • DCLRL (LREC) 2022 • Eirini Amanaki, Jean-Philippe Bernardy, Stergios Chatzikyriakidis, Robin Cooper, Simon Dobnik, Aram Karimi, Adam Ek, Eirini Chrysovalantou Giannikouri, Vasiliki Katsouli, Ilias Kolokousis, Eirini Chrysovalantou Mamatzaki, Dimitrios Papadakis, Olga Petrova, Erofili Psaltaki, Charikleia Soupiona, Effrosyni Skoulataki, Christina Stefanidou
First, we extend the Greek version of the FraCaS test suite to include examples where the inference is directly linked to the syntactic/morphological properties of Greek.
no code implementations • ACL (mmsr, IWCS) 2021 • Sharid Loáiciga, Simon Dobnik, David Schlangen
With this paper, we intend to start a discussion on the annotation of referential phenomena in situated dialogue.
no code implementations • INLG (ACL) 2020 • Nikolai Ilinykh, Simon Dobnik
Generating multi-sentence image descriptions is a challenging task, which requires a good model to produce coherent and accurate paragraphs, describing salient objects in the image.
Ranked #10 on Image Paragraph Captioning on Image Paragraph Captioning
no code implementations • OSACT (LREC) 2022 • Kathrein Abu Kwaik, Stergios Chatzikyriakidis, Simon Dobnik
The usage of social media platforms has resulted in the proliferation of work on Arabic Natural Language Processing (ANLP), including the development of resources.
no code implementations • NAACL (ALVR) 2021 • Sharid Loáiciga, Simon Dobnik, David Schlangen
We argue that there is still significant room for corpora that increase the complexity of both visual and linguistic domains and which capture different varieties of perceptual and conversational contexts.
1 code implementation • Findings (ACL) 2022 • Nikolai Ilinykh, Simon Dobnik
We explore how a multi-modal transformer trained for generation of longer image descriptions learns syntactic and semantic representations about entities and relations grounded in objects at the level of masked self-attention (text generation) and cross-modal attention (information fusion).
no code implementations • CLASP 2022 • Simon Dobnik, Robin Cooper, Adam Ek, Bill Noble, Staffan Larsson, Nikolai Ilinykh, Vladislav Maraev, Vidya Somashekarappa
In this paper we examine different meaning representations that are commonly used in different natural language applications today and discuss their limits, both in terms of the aspects of the natural language meaning they are modelling and in terms of the aspects of the application for which they are used.
no code implementations • PVLAM (LREC) 2022 • Nikolai Ilinykh, Rafal Černiavski, Eva Elžbieta Sventickaitė, Viktorija Buzaitė, Simon Dobnik
We conclude that face description generation systems are more susceptible to language rather than vision data augmentation.
no code implementations • PaM 2020 • José Miguel Cano Santín, Simon Dobnik, Mehdi Ghanimifard
The major shortcomings of using neural networks with situated agents are that in incremental interaction very few learning examples are available and that their visual sensory representations are quite different from image caption datasets.
no code implementations • COLING (CRAC) 2022 • Sharid Loáiciga, Simon Dobnik, David Schlangen
We present a first release of 500 documents from the multimodal corpus Tell-me-more (Ilinykh et al., 2019) annotated with coreference information according to the ARRAU guidelines (Poesio et al., 2021).
no code implementations • 30 Aug 2023 • Elena Volodina, Simon Dobnik, Therese Lindström Tiedemann, Xuan-Son Vu
Accessibility of research data is critical for advances in many research fields, but textual data often cannot be shared due to the personal and sensitive information which it contains, e. g names or political opinions.
no code implementations • 21 Apr 2022 • Aram Karimi, Simon Dobnik
Finding and selecting the most relevant scientific papers from a large number of papers written in a research community is one of the key challenges for researchers these days.
no code implementations • 10 Sep 2021 • Simon Dobnik, Robin Cooper, Adam Ek, Bill Noble, Staffan Larsson, Nikolai Ilinykh, Vladislav Maraev, Vidya Somashekarappa
In this paper we examine different meaning representations that are commonly used in different natural language applications today and discuss their limits, both in terms of the aspects of the natural language meaning they are modelling and in terms of the aspects of the application for which they are used.
no code implementations • WS 2020 • Yuri Bizzoni, Simon Dobnik
This work explores the differences and similarities between neural image classifiers{'} mis-categorisations and visually grounded metaphors - that we could conceive as intentional mis-categorisations.
no code implementations • LREC 2020 • Kathrein Abu Kwaik, Stergios Chatzikyriakidis, Simon Dobnik, Motaz Saad, Richard Johansson
As the number of social media users increases, they express their thoughts, needs, socialise and publish their opinions reviews.
no code implementations • WS 2019 • Wafia Adouane, Jean-Philippe Bernardy, Simon Dobnik
We work with Algerian, an under-resourced non-standardised Arabic variety, for which we compile a new parallel corpus consisting of user-generated textual data matched with normalised and corrected human annotations following data-driven and our linguistically motivated standard.
no code implementations • WS 2019 • Mehdi Ghanimifard, Simon Dobnik
The aim of this paper is to evaluate what representations facilitate generating image descriptions with spatial relations and lead to better grounded language generation.
no code implementations • WS 2019 • Wafia Adouane, Jean-Philippe Bernardy, Simon Dobnik
We explore the extent to which neural networks can learn to identify semantically equivalent sentences from a small variable dataset using an end-to-end training.
1 code implementation • WS 2019 • Mehdi Ghanimifard, Simon Dobnik
Understanding and generating spatial descriptions requires knowledge about what objects are related, their functional interactions, and where the objects are geometrically located.
no code implementations • 21 Jul 2018 • Simon Dobnik, John D. Kelleher
Natural language processing (NLP) can be done using either top-down (theory driven) and bottom-up (data driven) approaches, which we call mechanistic and phenomenological respectively.
no code implementations • 21 Jul 2018 • John D. Kelleher, Simon Dobnik
This paper examines to what degree current deep learning architectures for image caption generation capture spatial language.
no code implementations • WS 2018 • Wafia Adouane, Jean-Philippe Bernardy, Simon Dobnik
We explore the effect of injecting background knowledge to different deep neural network (DNN) configurations in order to mitigate the problem of the scarcity of annotated data when applying these models on datasets of low-resourced languages.
no code implementations • WS 2018 • Wafia Adouane, Simon Dobnik, Jean-Philippe Bernardy, Nasredine Semmar
This paper seeks to examine the effect of including background knowledge in the form of character pre-trained neural language model (LM), and data bootstrapping to overcome the problem of unbalanced limited resources.
no code implementations • WS 2018 • Simon Dobnik, Mehdi Ghanimifard, John Kelleher
The challenge for computational models of spatial descriptions for situated dialogue systems is the integration of information from different modalities.
no code implementations • WS 2017 • Wafia Adouane, Simon Dobnik
This paper presents a language identification system designed to detect the language of each word, in its context, in a multilingual documents as generated in social media by bilingual/multilingual communities, in our case speakers of Algerian Arabic.