Search Results for author: Sebastian Möller

Found 22 papers, 10 papers with code

Towards Hybrid Human-Machine Workflow for Natural Language Generation

no code implementations EACL (HCINLP) 2021 Neslihan Iskender, Tim Polzehl, Sebastian Möller

In recent years, crowdsourcing has gained much attention from researchers to generate data for the Natural Language Generation (NLG) tools or to evaluate them.

Text Generation

Reliability of Human Evaluation for Text Summarization: Lessons Learned and Challenges Ahead

1 code implementation EACL (HumEval) 2021 Neslihan Iskender, Tim Polzehl, Sebastian Möller

Based on our empirical analysis, we provide guidelines to ensure the reliability of expert and non-expert evaluations, and we determine the factors that might affect the reliability of the human evaluation.

Text Summarization

Best Practices for Crowd-based Evaluation of German Summarization: Comparing Crowd, Expert and Automatic Evaluation

no code implementations EMNLP (Eval4NLP) 2020 Neslihan Iskender, Tim Polzehl, Sebastian Möller

On the one hand, the human assessment of summarization quality conducted by linguistic experts is slow, expensive, and still not a standardized procedure.

Claim extraction from text using transfer learning.

no code implementations ICON 2020 Acharya Ashish Prabhakar, Salar Mohtaj, Sebastian Möller

Building an end to end fake news detection system consists of detecting claims in text and later verifying them for their authenticity.

Fake News Detection Transfer Learning

Simulating Turn-Taking in Conversations with Delayed Transmission

no code implementations SIGDIAL (ACL) 2020 Thilo Michael, Sebastian Möller

We show how the turn-taking mechanisms modeled for conversations without delay perform in scenarios with delay and identify to which extend the simulation is able to model the delayed turn-taking observed in human conversation.

Does Summary Evaluation Survive Translation to Other Languages?

no code implementations16 Sep 2021 Neslihan Iskender, Oleg Vasilyev, Tim Polzehl, John Bohannon, Sebastian Möller

The creation of a large summarization quality dataset is a considerable, expensive, time-consuming effort, requiring careful planning and setup.


Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools

2 code implementations EMNLP (ACL) 2021 Nils Feldhus, Robert Schwarzenberg, Sebastian Möller

To facilitate research, we present Thermostat which consists of a large collection of model explanations and accompanying analysis tools.

Towards Human-Free Automatic Quality Evaluation of German Summarization

no code implementations13 May 2021 Neslihan Iskender, Oleg Vasilyev, Tim Polzehl, John Bohannon, Sebastian Möller

Evaluating large summarization corpora using humans has proven to be expensive from both the organizational and the financial perspective.

Language Modelling

Full-Reference Speech Quality Estimation with Attentional Siamese Neural Networks

1 code implementation3 May 2021 Gabriel Mittags, Sebastian Möller

In this paper, we present a full-reference speech quality prediction model with a deep learning approach.

Speech Quality

Deep Learning Based Assessment of Synthetic Speech Naturalness

1 code implementation23 Apr 2021 Gabriel Mittag, Sebastian Möller

Further, we show that the reliability of deep learning-based naturalness prediction can be improved by transfer learning from speech quality prediction models that are trained on objective POLQA scores.

Speech Quality Speech Synthesis +2

Bias-Aware Loss for Training Image and Speech Quality Prediction Models from Multiple Datasets

2 code implementations20 Apr 2021 Gabriel Mittag, Saman Zadtootaghaj, Thilo Michael, Babak Naderi, Sebastian Möller

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.

Speech Quality

NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets

1 code implementation19 Apr 2021 Gabriel Mittag, Babak Naderi, Assmaa Chehadi, Sebastian Möller

In this paper, we present an update to the NISQA speech quality prediction model that is focused on distortions that occur in communication networks.

Speech Quality

Efficient Explanations from Empirical Explainers

2 code implementations EMNLP (BlackboxNLP) 2021 Robert Schwarzenberg, Nils Feldhus, Sebastian Möller

Amid a discussion about Green AI in which we see explainability neglected, we explore the possibility to efficiently approximate computationally expensive explainers.

Incorporating Wireless Communication Parameters into the E-Model Algorithm

no code implementations5 Mar 2021 Demóstenes Z. Rodríguez, Dick Carrillo Melgarejo, Miguel A. Ramírez, Pedro H. J. Nardelli, Sebastian Möller

However, the NB, WB, and FB E-model algorithms do not consider wireless techniques used in these networks, such as Multiple-Input-Multiple-Output (MIMO) systems, which are used to improve the communication system robustness in the presence of different types of wireless channel degradation.

Speech Quality

Fine-grained linguistic evaluation for state-of-the-art Machine Translation

no code implementations WMT (EMNLP) 2020 Eleftherios Avramidis, Vivien Macketanz, Ursula Strohriegel, Aljoscha Burchardt, Sebastian Möller

This paper describes a test suite submission providing detailed statistics of linguistic performance for the state-of-the-art German-English systems of the Fifth Conference of Machine Translation (WMT20).

Machine Translation Translation

Towards Deep Learning Methods for Quality Assessment of Computer-Generated Imagery

no code implementations2 May 2020 Markus Utke, Saman Zadtootaghaj, Steven Schmidt, Sebastian Möller

Video gaming streaming services are growing rapidly due to new services such as passive video streaming, e. g. Twitch. tv, and cloud gaming, e. g. Nvidia Geforce Now.

Impact of the Number of Votes on the Reliability and Validity of Subjective Speech Quality Assessment in the Crowdsourcing Approach

1 code implementation25 Mar 2020 Babak Naderi, Tobias Hossfeld, Matthias Hirth, Florian Metzger, Sebastian Möller, Rafael Zequeira Jiménez

The subjective quality of transmitted speech is traditionally assessed in a controlled laboratory environment according to ITU-T Rec.


Subjective Assessment of Text Complexity: A Dataset for German Language

no code implementations16 Apr 2019 Babak Naderi, Salar Mohtaj, Kaspar Ensikat, Sebastian Möller

This paper presents TextComplexityDE, a dataset consisting of 1000 sentences in German language taken from 23 Wikipedia articles in 3 different article-genres to be used for developing text-complexity predictor models and automatic text simplification in German language.

Text Simplification

Cannot find the paper you are looking for? You can Submit a new open access paper.