Chris Biemann

Chris Biemann
University of Hamburg | UHH · Department of Informatics

Prof. Dr. rer. nat.
Enabling and shaping the digital transformation of sciences and the humanities

About

286
Publications
96,759
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
4,843
Citations
Citations since 2016
184 Research Items
3782 Citations
20162017201820192020202120220200400600
20162017201820192020202120220200400600
20162017201820192020202120220200400600
20162017201820192020202120220200400600
Introduction
Chris Biemann currently works at the Department of Informatics, University of Hamburg. Chris does research in Artificial Intelligence, Human-computer Interaction and Computational Linguistics.
Additional affiliations
April 2011 - present
Technische Universität Darmstadt
Position
  • Professor (Assistant)
September 2008 - October 2010
Microsoft
Position
  • Research Software Dev Lead
April 2003 - January 2008
University of Leipzig

Publications

Publications (286)
Conference Paper
Full-text available
Most existing methods to measure social bias in natural language generation are specifiedfor English language models. In this work, we developed a German regard classifier based on a newlycrowd-sourced dataset. Our model meets the test set accuracy of the original English version. Withthe classifier, we measured binary gender bias in two large lang...
Conference Paper
Full-text available
We investigate the semantic retrieval potential of pre-trained contextualized word embeddings (CWEs) such as BERT, in combination with explicit linguistic information, for various NLP tasks in an information retrieval setup. In this paper, we compare different strategies to aggregate contextualized word embeddings along lexical, syntactic, or gramm...
Chapter
This paper is a condensed report on the third year of the Touché lab on argument retrieval held at CLEF 2022. With the goal to foster and support the development of technologies for argument mining and argument analysis, we organized three shared tasks in the third edition of Touché: (a) argument retrieval for controversial topics, where participan...
Conference Paper
Full-text available
The corona pandemic and countermeasures such as social distancing and lockdowns have confronted individuals with new challenges for their mental health and well-being. It can be assumed that the Jungian psychology types of extraverts and introverts react differently to these challenges. We propose a Bi-LSTM model with an attention mechanism for cla...
Chapter
Under the umbrella of the D-WISE project, manual and digital approaches to discourse analysis are combined to develop a prototypical working environment for digital qualitative discourse analysis. This new qualitative data analysis tool, called D-WISE Tool Suite, is built up in a process of close exchange by the two teams from humanities and inform...
Conference Paper
We present a dataset containing source code solutions to algorithmic programming exercises solved by hundreds of Bachelor-level students at the Universität Hamburg. These solutions were collected during the winter semesters 2019/2020, 2020/2021 and 2021/2022. The dataset contains a set of solutions to a total of 21 tasks written in Java as well as...
Preprint
Full-text available
In this work, we focus on the task of generating SPARQL queries from natural language questions, which can then be executed on Knowledge Graphs (KGs). We assume that gold entity and relations have been provided, and the remaining task is to arrange them in the right order along with SPARQL vocabulary, and input tokens to produce the correct SPARQL...
Article
Full-text available
This survey presents a comprehensive description of recent neural entity linking (EL) systems developed since 2015 as a result of the “deep learning revolution” in natural language processing. Its goal is to systemize design features of neural entity linking systems and compare their performance to the remarkable classic methods on common benchmark...
Preprint
Full-text available
We present Sense Clustering over Time (SCoT), a novel network-based tool for analysing lexical change. SCoT represents the meanings of a word as clusters of similar words. It visualises their formation, change, and demise. There are two main approaches to the exploration of dynamic networks: the discrete one compares a series of clustered graphs fr...
Article
Full-text available
Though there is a strong consensus that word length and frequency are the most important single-word features determining visual-orthographic access to the mental lexicon, there is less agreement as how to best capture syntactic and semantic factors. The traditional approach in cognitive reading research assumes that word predictability from senten...
Preprint
Full-text available
Though there is a strong consensus that word length and frequency are the most important single-word features determining visual-orthographic access to the mental lexicon, there is less agreement as how to best capture syntactic and semantic factors. The traditional approach in cognitive reading research assumes that word predictability from senten...
Chapter
The goal of the Touché lab on argument retrieval is to foster and support the development of technologies for argument mining and argument analysis. In the third edition of Touché, we organize three shared tasks: (a) argument retrieval for controversial topics, where participants retrieve a gist of arguments from a collection of online debates, (b)...
Conference Paper
Full-text available
Transformer-based language models recently gained large popularity in Natural Language Processing (NLP) because of their diverse applicability in various tasks where they reach state-of-the-art performance. Even though for resource-rich languages like English, performance is very high, there is still headroom for improvement for low resource langua...
Article
Full-text available
The availability of different pre-trained semantic models has enabled the quick development of machine learning components for downstream applications. However, even if texts are abundant for low-resource languages, there are very few semantic models publicly available. Most of the publicly available pre-trained models are usually built as a multil...
Article
Numerous attempts for hypernymy relation (e.g. dog `is-a' animal) detection have been made for resourceful languages like English, whereas efforts made for low-resource languages are scarce primarily due to lack of gold standard datasets and suitable distributional models. Therefore, we introduce four gold standard datasets for hypernymy detection...
Chapter
Full-text available
This paper is a condensed report on the second year of the Touché shared task on argument retrieval held at CLEF 2021. With the goal to provide a collaborative platform for researchers, we organized two tasks: (1) supporting individuals in finding arguments on controversial topics of social importance and (2) supporting individuals with arguments i...
Preprint
Full-text available
In this research, we investigate techniques to detect hate speech in movies. We introduce a new dataset collected from the subtitles of six movies, where each utterance is annotated either as hate, offensive or normal. We apply transfer learning techniques of domain adaptation and fine-tuning on existing social media datasets, namely from Twitter a...
Conference Paper
Full-text available
In primary school, children's books, as well as in modern language learning apps, multi-modal learning strategies like illustrations of terms and phrases are used to support reading comprehension. Also, several studies in educational psychology suggest that integrating cross-modal information will improve reading comprehension. We claim that state-...
Article
Full-text available
Hate speech is a challenging issue plaguing the online social media. While better models for hate speech detection are continuously being developed, there is little research on the bias and interpretability aspects of hate speech. In this paper, we introduce HateXplain, the first benchmark hate speech dataset covering multiple aspects of the issue....
Conference Paper
Full-text available
Recent research using pre-trained language models for multi-document summarization tasks lacks a deep investigation of potential erroneous cases and their possible application in other languages. In this work, we apply a pre-trained language model (BART) for multi-document summarization (MDS) task, both with fine-tuning and without fine-tuning. We...
Conference Paper
Full-text available
To build machine learning-based applications for sensitive domains like medical, legal, etc. where the digitized text contains private information , anonymization of text is required for preserving privacy. Sequence tagging, e.g. as used for Named Entity Recognition (NER), can help to detect private information. However , to train sequence tagging...
Chapter
Full-text available
Technologies for argument mining and argumentation analysis are maturing rapidly, so that, as a result, the retrieval of arguments in search scenarios becomes a feasible objective. For the second time, we organize the Touché lab on argument retrieval with two shared tasks: (1) argument retrieval for controversial questions, where arguments are to b...
Preprint
Full-text available
Hate speech is a challenging issue plaguing the online social media. While better models for hate speech detection are continuously being developed, there is little research on the bias and interpretability aspects of hate speech. In this paper, we introduce HateXplain, the first benchmark hate speech dataset covering multiple aspects of the issue....
Conference Paper
Full-text available
The COVID-19 pandemic has caused international social tension and unrest. Besides the crisis itself, there are growing signs of rising conflict potential of societies around the world. Indicators of global mood changes are hard to detect and direct questionnaires suffer from social desirability biases. However, so-called implicit methods can reveal...
Preprint
Full-text available
The COVID-19 pandemic has caused international social tension and unrest. Besides the crisis itself, there are growing signs of rising conflict potential of societies around the world. Indicators of global mood changes are hard to detect and direct questionnaires suffer from social desirability biases. However, so-called implicit methods can reveal...
Preprint
Full-text available
The availability of different pre-trained semantic models enabled the quick development of machine learning components for downstream applications. Despite the availability of abundant text data for low resource languages, only a few semantic models are publicly available. Publicly available pre-trained models are usually built as a multilingual ve...
Preprint
Full-text available
The corpus, from which a predictive language model is trained, can be considered the experience of a semantic system. We recorded everyday reading of two participants for two months on a tablet, generating individual corpus samples of 300/500K tokens. Then we trained word2vec models from individual corpora and a 70 million-sentence newspaper corpus...
Conference Paper
Full-text available
The corpus, from which a predictive language model is trained, can be considered the experience of a semantic system. We recorded everyday reading of two participants for two months on a tablet, generating individual corpus samples of 300/500K tokens. Then we trained word2vec models from individual corpora and a 70 million-sentence newspaper corpus...
Conference Paper
Full-text available
In this paper, we describe our lessons learned during the introduction of automatically assessed programming exercises to a Bachelor's level course on algorithms and data structures in the Winter semester 2019/2020, which is yearly taken by around 300 students. The course used to mostly focus on theoretical and formal aspects of selected algorithms...
Chapter
Full-text available
Argumentation is essential for opinion formation when it comes to debating on socially important topics as well as when making everyday personal decisions. The web provides an enormous source of argumentative texts, where well-reasoned argumentations are mixed with biased, faked, and populist ones.The research direction of developing argument retri...
Conference Paper
Full-text available
The use of Intelligence Quotient (IQ) testing as a measure for intellectual ability is controversial. Even though IQ testing is considered to be among the most valid measures of psychology, findings and current research sparked a debate over racial or socioeconomic biases, as well as the label of 'pseudoscience' for many situations that involve IQ...
Conference Paper
Full-text available
This paper describes the tasks, databases, baseline systems, and summarizes submissions and results for the GermEval 2020 Shared Task 1 on the Classification and Regression of Cognitive and Motivational Style from Text. This shared task is divided into two subtasks, a regression task, and a classification task. Subtask 1 asks participants to reprod...
Article
Full-text available
Question answering platforms such as Yahoo! Answers or Quora always contained questions that ask other humans for help when comparing two or more options. Since nowadays more and more people also “talk” to their devices, such comparative questions are also part of the query stream that major search engines receive. Interestingly, major search engin...
Preprint
Full-text available
While word predictability from sentence context is typically investigated by cloze completion probabilities (CCP), it can be more deeply understood by relying on language models (LMs), allowing to define the three key components of memory: Memory starts with experience as implemented by a text corpus, here defined by Wikipedia capturing general kno...
Preprint
Full-text available
In this survey, we provide a comprehensive description of recent neural entity linking (EL) systems. We distill their generic architecture that includes candidate generation, entity ranking, and unlinkable mention prediction components. For each of them, we summarize the prominent methods and models, including approaches to mention encoding based o...
Preprint
Full-text available
The Sparsespeech model is an unsupervised acoustic model that can generate discrete pseudo-labels for untranscribed speech. We extend the Sparsespeech model to allow for sampling over a random discrete variable, yielding pseudo-posteriorgrams. The degree of sparsity in this posteriorgram can be fully controlled after the model has been trained. We...
Preprint
Full-text available
Fine-tuning of pre-trained transformer networks such as BERT yield state-of-the-art results for text classification tasks. Typically, fine-tuning is performed on task-specific training datasets in a supervised manner. One can also fine-tune in unsupervised manner beforehand by further pre-training the masked language modeling (MLM) task. Hereby, in...
Chapter
Full-text available
Technologies for argument mining and argumentation processing are maturing continuously, giving rise to the idea of retrieving arguments in search scenarios. We introduce Touché, the first lab on Argument Retrieval featuring two subtasks: (1) the retrieval of arguments from a focused debate collection to support argumentative conversations, and (2)...
Preprint
Full-text available
Disambiguation of word senses in context is easy for humans, but is a major challenge for automatic approaches. Sophisticated supervised and knowledge-based models were developed to solve this task. However, (i) the inherent Zipfian distribution of supervised training instances for a given word and/or (ii) the quality of linguistic knowledge repres...
Preprint
Full-text available
We present the first approach to automatically building resources for academic writing. The aim is to build a writing aid system that automatically edits a text so that it better adheres to the academic style of writing. On top of existing academic resources, such as the Corpus of Contemporary American English (COCA) academic Word List, the New Aca...
Conference Paper
Full-text available
We analyze comparative questions, i.e., questions asking to compare different items that were submitted to Yandex in 2012. Responses to such questions might be quite different from the simple “ten blue links” and could, for example, aggregate pros and cons of the different options as direct answers. However, changing the result presentation is an i...