Search Results for author: Georg Groh

Found 35 papers, 11 papers with code

GrammarSHAP: An Efficient Model-Agnostic and Structure-Aware NLP Explainer

no code implementations LNLS (ACL) 2022 Edoardo Mosca, Defne Demirtürk, Luca Mülln, Fabio Raffagnato, Georg Groh

Interpreting NLP models is fundamental for their development as it can shed light on hidden properties and unexpected behaviors.

Constituency Parsing

User Satisfaction Modeling with Domain Adaptation in Task-oriented Dialogue Systems

no code implementations SIGDIAL (ACL) 2022 Yan Pan, Mingyang Ma, Bernhard Pflugfelder, Georg Groh

To the best of our knowledge, this is the first work to study user satisfaction estimation with unsupervised domain adaptation from chitchat to task-oriented dialogue.

Action Recognition Task-Oriented Dialogue Systems +1

Detecting Word-Level Adversarial Text Attacks via SHapley Additive exPlanations

no code implementations RepL4NLP (ACL) 2022 Edoardo Mosca, Lukas Huber, Marc Alexander Kühn, Georg Groh

State-of-the-art machine learning models are prone to adversarial attacks”:" Maliciously crafted inputs to fool the model into making a wrong prediction, often with high confidence.

Adversarial Text

SHAP-Based Explanation Methods: A Review for NLP Interpretability

no code implementations COLING 2022 Edoardo Mosca, Ferenc Szigeti, Stella Tragianni, Daniel Gallagher, Georg Groh

Model explanations are crucial for the transparent, safe, and trustworthy deployment of machine learning models.

Investigating Annotator Bias in Abusive Language Datasets

no code implementations RANLP 2021 Maximilian Wich, Christian Widmer, Gerhard Hagerer, Georg Groh

A prevalent form of bias in hate speech and abusive language datasets is annotator bias caused by the annotator’s subjective perception and the complexity of the annotation task.

Abusive Language

Investigating Annotator Bias with a Graph-Based Approach

1 code implementation EMNLP (ALW) 2020 Maximilian Wich, Hala Al Kuwatly, Georg Groh

In the scope of this study, we want to investigate annotator bias — a form of bias that annotators cause due to different knowledge in regards to the task and their subjective perception.

BIG-bench Machine Learning Community Detection +1

This is not correct! Negation-aware Evaluation of Language Generation Systems

3 code implementations26 Jul 2023 Miriam Anschütz, Diego Miguel Lozano, Georg Groh

Based on this dataset, we fine-tuned a sentence transformer and an evaluation metric to improve their negation sensitivity.

Embeddings Evaluation Text Generation

Adam-Smith at SemEval-2023 Task 4: Discovering Human Values in Arguments with Ensembles of Transformer-based Models

no code implementations15 May 2023 Daniel Schroter, Daryna Dementieva, Georg Groh

This paper presents the best-performing approach alias "Adam Smith" for the SemEval-2023 Task 4: "Identification of Human Values behind Arguments".

AdamR at SemEval-2023 Task 10: Solving the Class Imbalance Problem in Sexism Detection with Ensemble Learning

no code implementations15 May 2023 Adam Rydelek, Daryna Dementieva, Georg Groh

The Explainable Detection of Online Sexism task presents the problem of explainable sexism detection through fine-grained categorisation of sexist cases with three subtasks.

Data Augmentation Ensemble Learning

IFAN: An Explainability-Focused Interaction Framework for Humans and NLP Models

no code implementations6 Mar 2023 Edoardo Mosca, Daryna Dementieva, Tohid Ebrahim Ajdari, Maximilian Kummeth, Kirill Gringauz, Georg Groh

Interpretability and human oversight are fundamental pillars of deploying complex NLP models into real-world applications.

From Judgement's Premises Towards Key Points

no code implementations23 Dec 2022 Oren Sultan, Rayen Dhahri, Yauheni Mardan, Tobias Eder, Georg Groh

Key Point Analysis(KPA) is a relatively new task in NLP that combines summarization and classification by extracting argumentative key points (KPs) for a topic from a collection of texts and categorizing their closeness to the different arguments.

Retrieving Users' Opinions on Social Media with Multimodal Aspect-Based Sentiment Analysis

1 code implementation27 Oct 2022 Miriam Anschütz, Tobias Eder, Georg Groh

Then, the pipeline uses image retrieval to find all images showing similar content and applies aspect-based sentiment analysis to outline users' opinions about the selected term.

Aspect-Based Sentiment Analysis (ABSA) Image Retrieval +1

How to Build Robust FAQ Chatbot with Controllable Question Generator?

no code implementations18 Nov 2021 Yan Pan, Mingyang Ma, Bernhard Pflugfelder, Georg Groh

Many unanswerable adversarial questions fool the question-answer (QA) system with some plausible answers.

Chatbot Passage Retrieval +3

A Case Study and Qualitative Analysis of Simple Cross-Lingual Opinion Mining

1 code implementation3 Nov 2021 Gerhard Johann Hagerer, Wing Sheung Leung, Qiaoxi Liu, Hannah Danner, Georg Groh

User-generated content from social media is produced in many languages, making it technically challenging to compare the discussed themes from one domain across different cultures and regions.

Marketing Natural Language Understanding +2

An Analysis of Programming Course Evaluations Before and After the Introduction of an Autograder

no code implementations28 Oct 2021 Gerhard Johann Hagerer, Laura Lahesoo, Miriam Anschütz, Stephan Krusche, Georg Groh

Commonly, introductory programming courses in higher education institutions have hundreds of participating students eager to learn to program.

SocialVisTUM: An Interactive Visualization Toolkit for Correlated Neural Topic Models on Social Media Opinion Mining

no code implementations RANLP 2021 Gerhard Johann Hagerer, Martin Kirchhoff, Hannah Danner, Robert Pesch, Mainak Ghosh, Archishman Roy, Jiaxi Zhao, Georg Groh

In this paper, we demonstrate how these methods can be used to display correlated topic models on social media texts using SocialVisTUM, our proposed interactive visualization toolkit.

Opinion Mining Topic Models

Introducing an Abusive Language Classification Framework for Telegram to Investigate the German Hater Community

no code implementations15 Sep 2021 Maximilian Wich, Adrian Gorniak, Tobias Eder, Daniel Bartmann, Burak Enes Çakici, Georg Groh

Since traditional social media platforms continue to ban actors spreading hate speech or other forms of abusive languages (a process known as deplatforming), these actors migrate to alternative platforms that do not moderate users content.

Abusive Language Classification +1

Classification of Consumer Belief Statements From Social Media

no code implementations29 Jun 2021 Gerhard Johann Hagerer, Wenbin Le, Hannah Danner, Georg Groh

For scenario b) we compare abstract class labels given by the domain expert as baseline and by automatic hierarchical clustering.

Clustering Opinion Mining +2

GraphTMT: Unsupervised Graph-based Topic Modeling from Video Transcripts

1 code implementation4 May 2021 Lukas Stappen, Jason Thies, Gerhard Hagerer, Björn W. Schuller, Georg Groh

To unfold the tremendous amount of multimedia data uploaded daily to social media platforms, effective topic modeling techniques are needed.

Clustering Topic Models +1

Sequence Labeling: A Practical Approach

1 code implementation12 Aug 2018 Adnan Akhundov, Dietrich Trautmann, Georg Groh

We take a practical approach to solving sequence labeling problem assuming unavailability of domain expertise and scarcity of informational and computational resources.

Chunking NER +1

An evaluation of keyword extraction from online communication for the characterisation of social relations

no code implementations11 Feb 2014 Jan Hauffa, Tobias Lichtenberg, Georg Groh

The set of interpersonal relationships on a social network service or a similar online community is usually highly heterogenous.

Keyword Extraction

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