Sebastian Möller's research while affiliated with Deutsches Forschungszentrum für Künstliche Intelligenz and other places

Publications (476)

Chapter
In this chapter, we analyse influencing factors for the assessment of user experience (UX) from a chatbot operating in the domain of technical customer support. To find out which UX factors can be assessed reliably in a crowdsourcing setup, we conduct a crowd-based UX assessment study through a set of scenario-based tasks and analyse the UX assessm...
Preprint
Full-text available
Saliency maps can explain a neural model's prediction by identifying important input features. While they excel in being faithful to the explained model, saliency maps in their entirety are difficult to interpret for humans, especially for instances with many input features. In contrast, natural language explanations (NLEs) are flexible and can be...
Conference Paper
Full-text available
Das Projekt "Instrumente zur aktiven und sicheren Verbraucherteilhabe an Online Public Services" (IVTOPS) analysiert die Verbraucherakzeptanz von öffentlichen Online-Dienste am Beispiel von Nutzerkonten in Berlin und Brandenburg, um geeignete Instrumente zur Überwindung von Akzeptanzbarrieren bzw. Informations- und digitalen Kompetenzasymmetrien be...
Article
Full-text available
Patient care after kidney transplantation requires integration of complex information to make informed decisions on risk constellations. Many machine learning models have been developed for detecting patient outcomes in the past years. However, performance metrics alone do not determine practical utility. We present a newly developed clinical decis...
Chapter
Social media have been growing rapidly during past years. They changed different aspects of human life, especially how people communicate and also how people access information. However, along with the important benefits, social media causes a number of significant challenges since they were introduced. Spreading of fake news and hate speech are am...
Chapter
Angewandte Forschung in der Wirtschaftsinformatik 2022 Tagungsband zur 35. Jahrestagung des Arbeitskreises Wirtschaftsinformatik an Hochschulen für Angewandte Wissenschaften im deutschsprachigen Raum (AKWI) vom 11.09. bis 13.09.2022, ausgerichtet von der Hochschule für Technik und Wirtschaft Berlin (HTW Berlin) und der Hochschule für Wirtschaft und...
Conference Paper
Android applications request specific permissions from users during the installations to perform required functionalities by accessing system resources and personal information. Usually, users must approve the permissions requested by applications (apps) during the installation process and before the apps can collect privacy- or security-relevant i...
Preprint
Full-text available
In this work, we present the first corpus for German Adverse Drug Reaction (ADR) detection in patient-generated content. The data consists of 4,169 binary annotated documents from a German patient forum, where users talk about health issues and get advice from medical doctors. As is common in social media data in this domain, the class labels of th...
Chapter
Fake news spreading through social media has become a serious problem in recent years, especially after the United States presidential election in 2016. Accordingly, more attention has been paid to this issue by scientists to develop automated tools to combat those pieces of information that contain misinformation, using natural language processing...
Preprint
Full-text available
Text readability assessment has a wide range of applications for different target people, from language learners to people with disabilities. The fast pace of textual content production on the web makes it impossible to measure text complexity without the benefit of machine learning and natural language processing techniques. Although various resea...
Preprint
Full-text available
Background: In the information extraction and natural language processing domain, accessible datasets are crucial to reproduce and compare results. Publicly available implementations and tools can serve as benchmark and facilitate the development of more complex applications. However, in the context of clinical text processing the number of accessi...
Preprint
Full-text available
The human-centric explainable artificial intelligence (HCXAI) community has raised the need for framing the explanation process as a conversation between human and machine. In this position paper, we establish desiderata for Mediators, text-based conversational agents which are capable of explaining the behavior of neural models interactively using...
Chapter
Virtual Reality (VR) technology is mostly used in gaming, videos, engineering applications, and training simulators. One thing which is shared among all of them is the necessity to display text. Text reading experience is not always in focus for VR systems because of limited hardware capabilities, lack of standardization, user interface (UI) design...
Article
Full-text available
Question Answering (QA) is a field of study addressed to develop automatic methods for answering questions expressed in natural language. Recently, the emergence of the new generation of intelligent assistants, such as Siri, Alexa, and Google Assistant, has intensified the importance of an effective and efficient QA system able to handle questions...
Chapter
Recently, Augmented Reality (AR) applications have emerged as a powerful tool to empower users in touristic use cases, for example, by recreating digital representations of lost or difficult accessible artifacts. More emphasis has been put on researching possible solutions for tourism with AR technology. As part of such a research project, an AR to...
Preprint
Full-text available
Patient care after kidney transplantation requires integration of complex information to make informed decisions on risk constellations. Many machine learning models have been developed for detecting patient outcomes in the past years. However, performance metrics alone do not determine practical utility. Often, the actual performance of medical pr...
Preprint
Full-text available
Scientific publications about machine learning in healthcare are often about implementing novel methods and boosting the performance - at least from a computer science perspective. However, beyond such often short-lived improvements, much more needs to be taken into consideration if we want to arrive at a sustainable progress in healthcare. What do...
Preprint
Full-text available
In our previous work, we derived the acoustic features, that contribute to the perception of warmth and competence in synthetic speech. As an extension, in our current work, we investigate the impact of the derived vocal features in the generation of the desired characteristics. The acoustic features, spectral flux, F1 mean and F2 mean and their co...
Preprint
Full-text available
With the advances in speech communication systems such as online conferencing applications, we can seamlessly work with people regardless of where they are. However, during online meetings, speech quality can be significantly affected by background noise, reverberation, packet loss, network jitter, etc. Because of its nature, speech quality is trad...
Poster
Full-text available
Instrumente zur aktiven und sicheren Verbraucherteilhabe an Online Public Services (IVTOPS): Im Projekt wird die Akzeptanz von Servicekonten aus der Perspektive des Digital Divide mit qualitativen (Experteninterviews) und quantitativen Methoden (Umfrage) analysiert.
Chapter
Full-text available
This paper describes the development of the first test suite for the language direction Portuguese-English. Designed for fine-grained linguistic analysis, the test suite comprises 330 test sentences for 66 linguistic phenomena and 14 linguistic categories. Eight different MT systems were compared using quantitative and qualitative methods via the t...
Article
Full-text available
This study investigates effects of spatial auditory cues on human listeners' response strategy for identifying two alternately active talkers (“turn-taking” listening scenario). Previous research has demonstrated subjective benefits of audio spatialization with regard to speech intelligibility and talker-identification effort. So far, the deliberat...
Preprint
Full-text available
Vocabulary learning is vital to foreign language learning. Correct and adequate feedback is essential to successful and satisfying vocabulary training. However, many vocabulary and language evaluation systems perform on simple rules and do not account for real-life user learning data. This work introduces Multi-Language Vocabulary Evaluation Data S...
Preprint
Full-text available
The detection of hate speech online has become an important task, as offensive language such as hurtful, obscene and insulting content can harm marginalized people or groups. This paper presents TU Berlin team experiments and results on the task 1A and 1B of the shared task on hate speech and offensive content identification in Indo-European langua...
Article
Full-text available
Gaming video streaming services are growing rapidly due to new services such as passive video streaming of gaming content, e.g. Twitch.tv, as well as cloud gaming, e.g. Nvidia GeForce NOW and Google Stadia. In contrast to traditional video content, gaming content has special characteristics such as extremely high and special motion patterns, synthe...
Article
Full-text available
Subjective speech quality assessment has traditionally been carried out in laboratory environments under controlled conditions. With the advent of crowdsourcing platforms tasks, which need human intelligence, can be resolved by crowd workers over the Internet. Crowdsourcing also offers a new paradigm for speech quality assessment, promising higher...
Conference Paper
Full-text available
We are using a semi-automated test suite in order to provide a fine-grained linguistic evaluation for state-of-the-art machine translation systems. The evaluation includes 18 German to English and 18 English to German systems, submitted to the Translation Shared Task of the 2021 Conference on Machine Translation. Our submission adds up to the submi...
Article
Full-text available
As working and learning environments become open and flexible, people are also potentially surrounded by ambient noise, which causes an increase in mental workload. The present study uses electroencephalogram (EEG) and subjective measures to investigate if noise-canceling technologies can fade out external distractions and free up mental resources....
Conference Paper
Full-text available
The standard approach of Notice and Choice does not provide sufficient control over personal privacy preferences. A more granular analysis of privacy preferences is needed where the monetary valuation of different data types can contribute to the understanding of individual privacy concerns of personal information. The question of how much consumer...
Preprint
Full-text available
The creation of a quality summarization dataset is an expensive, time-consuming effort, requiring the production and evaluation of summaries by both trained humans and machines. If such effort is made in one language, it would be beneficial to be able to use it in other languages without repeating human annotations. To investigate how much we can t...
Conference Paper
Full-text available
Amid a discussion about Green AI in which we see explainability neglected, we explore the possibility to efficiently approximate computa-tionally expensive explainers. To this end, we propose feature attribution modelling with Empirical Explainers. Empirical Explainers learn from data to predict the attribution maps of expensive explainers. We trai...
Conference Paper
Full-text available
In the language domain, as in other domains, neural explainability takes an ever more important role, with feature attribution methods on the forefront. Many such methods require considerable computational resources and expert knowledge about implementation details and parameter choices. To facilitate research , we present THERMOSTAT which consists...
Preprint
Full-text available
In the language domain, as in other domains, neural explainability takes an ever more important role, with feature attribution methods on the forefront. Many such methods require considerable computational resources and expert knowledge about implementation details and parameter choices. To facilitate research, we present Thermostat which consists...
Article
Full-text available
One of the challenges during the post-COVID pandemic era will be to foster social connections between people. Previous research suggests that people who is able to regulate their emotions tends to have better social connections with others. Additional studies indicate that it is possible to train the ability to regulate emotions voluntarily, using...
Article
Full-text available
A cluster of research in Affective Computing suggests that it is possible to infer some characteristics of users’ affective states by analyzing their electrophysiological activity in real-time. However, it is not clear how to use the information extracted from electrophysiological signals to create visual representations of the affective states of...
Conference Paper
Full-text available
The advent of neural Text-to-Speech (TTS) synthesizers has enhanced the expressivity of synthetic speech in the recent past. However, there is very little work on understanding the acoustic correlates of paralinguistic traits, emotions, speaker attributes and characteristics from synthetic speech. This paper investigates the acoustic correlates of...
Article
Full-text available
Objectives To investigate global and momentary effects of a tablet-based non-pharmacological intervention for nursing home residents living with dementia. Design Cluster-randomized controlled trial. Setting Ten nursing homes in Germany were randomly allocated to the tablet-based intervention (TBI, 5 units) or conventional activity sessions (CAS,...
Chapter
Full-text available
One of the main challenges in the development of argument mining tools is the availability of annotated data of adequate size and quality. However, generating data sets using experts is expensive from both organizational and financial perspectives, which is also the case for tools developed for identifying argumentative content in informal social m...
Conference Paper
Full-text available
With the improved computational abilities, the usage of chat-bots and conversational agents has become more prevalent. Therefore, it is essential that these agents exhibit certain social speaker characteristics in the generated speech. In this paper , we study the perception of such speaker characteristics in two commercial Text-to-Speech (TTS) sys...
Preprint
BACKGROUND Mobile application-based therapies are increasingly being employed by speech-language pathologists in the rehabilitation of people with aphasia (PwA) as an adjunct or in lieu of traditional in-person therapy approaches. These apps can increase the intensity of treatment, and have been shown to result in meaningful outcomes across several...
Article
Full-text available
Background Mobile app–based therapies are increasingly being employed by speech-language pathologists in the rehabilitation of people with aphasia as adjuncts or substitutes for traditional in-person therapy approaches. These apps can increase the intensity of treatment and have resulted in meaningful outcomes across several domains. Objective Voic...
Preprint
Full-text available
Evaluating large summarization corpora using humans has proven to be expensive from both the organizational and the financial perspective. Therefore, many automatic evaluation metrics have been developed to measure the summarization quality in a fast and reproducible way. However, most of the metrics still rely on humans and need gold standard summ...
Preprint
In this paper, we present a new objective prediction model for synthetic speech naturalness. It can be used to evaluate Text-To-Speech or Voice Conversion systems and works language independently. The model is trained end-to-end and based on a CNN-LSTM network that previously showed to give good results for speech quality estimation. We trained and...
Preprint
The ground truth used for training image, video, or speech quality prediction models is based on the Mean Opinion Scores (MOS) obtained from subjective experiments. Usually, it is necessary to conduct multiple experiments, mostly with different test participants, to obtain enough data to train quality models based on machine learning. Each of these...
Conference Paper
Full-text available
In recent years, crowdsourcing has gained much attention from researchers to generate data for the Natural Language Generation (NLG) tools or to evaluate them. However, the quality of crowdsourced data has been questioned repeatedly because of the complexity of NLG tasks and crowd workers{'} unknown skills. Moreover, crowdsourcing can also be costl...
Conference Paper
Full-text available
Only a small portion of research papers with human evaluation for text summarization provide information about the participant demographics, task design, and experiment protocol. Additionally, many researchers use human evaluation as gold standard without questioning the reliability or investigating the factors that might affect the reliability of...
Preprint
In this paper, we present an update to the NISQA speech quality prediction model that is focused on distortions that occur in communication networks. In contrast to the previous version, the model is trained end-to-end and the time-dependency modelling and time-pooling is achieved through a Self-Attention mechanism. Besides overall speech quality,...
Preprint
Traditionally, Quality of Experience (QoE) for a communication system is evaluated through a subjective test. The most common test method for speech QoE is the Absolute Category Rating (ACR), in which participants listen to a set of stimuli, processed by the underlying test conditions, and rate their perceived quality for each stimulus on a specifi...
Book
Full-text available
Communication Acoustics deals with the fundamentals of those areas of acoustics which are related to modern communication technologies. Due to the advent of digital signal processing and recording in acoustics, these areas have enjoyed an enormous upswing during the last 4 decades. The book chapters represent review articles covering the most relev...
Preprint
Full-text available
Amid a discussion about Green AI in which we see explainability neglected, we explore the possibility to efficiently approximate computationally expensive explainers. To this end, we propose the task of feature attribution modelling that we address with Empirical Explainers. Empirical Explainers learn from data to predict the attribution maps of ex...
Preprint
One of the challenges during the post-COVID pandemic era will be to foster social connections between people. Previous research suggests that people who is able to regulate their emotions tends to have better social connections with others. Additional studies indicate that it is possible to train the ability to regulate emotions voluntarily, using...
Preprint
Full-text available
The spreading of disinformation throughout the web has become a critical problem for a democratic society. The dissemination of fake news has become a profitable business and a common practice among politicians and content producers. On the other hand, journalists and fact-checkers work unceasingly to debunk misinformation and prevent it from furth...
Article
Recent medical prognostic models adapted from high data-resource fields like language processing have quickly grown in complexity and size. However, since medical data typically constitute low data-resource settings, performances on tasks like clinical prediction did not improve expectedly. Instead of following this trend of using complex neural mo...
Preprint
Full-text available
A cluster of research in Human-Computer Interaction (HCI) suggests that it is possible to infer some characteristics of users' mental states by analyzing electrophysiological responses in real-time. However, it is not clear how to use the information extracted from electrophysiological signals to create visual representations of the emotional state...
Preprint
UNSTRUCTURED The Covid-19 pandemic has put new demands on the medical systems worldwide. The pressure of taking far-reaching decisions within multiply limited resources under the constraint that personal contact must be minimized has evoked the question if technical support in the form of Artificial Intelligence (AI) could help leverage these chall...
Preprint
Speech communication systems based on Voice-over-IP technology are frequently used by native as well as non-native speakers of a target language, e.g. in international phone calls or telemeetings. Frequently, such calls also occur in a noisy environment, making noise suppression modules necessary to increase perceived quality of experience. Whereas...