Open Theses

Open Theses

  • 2019/07/24

    Automatic Metaphor Detection

    Bachelor Thesis, Master Thesis

    Metaphors permeate our everyday lives, and if you look closely, we are almost drowning in a sea of metaphors. Yet, to pinpoint them in text, especially in historical or scientific text, is a task still waiting for a satisfactorily solution. And there’s even more: different metaphor theories are fighting for our attention, each in need of a particular treatment – or can we catch all with the same net? Either way, linguists and philosophers will be hungry for your results! go

    Supervisors: Prof. Dr. Iryna Gurevych, Dipl.-Math. Erik-Lân Do Dinh

  • 2019/06/13

    Generating Text from Graph-based Data

    Bachelor Thesis, Master Thesis

    Recently, graph-to-sequence models have been applied to the task of text generation from structured data. Usually, these models incorporate Graph Neural Networks (GNNs) as graph encoders for learning effective graph representations. For instance, given a knowledge graph, we are interested in verbalizing a text that reproduces the information contained in the graph. The goal of this project is to develop and research deep learning techniques to generate textual information from graph-based data, such as meaning representations and knowledge graphs. go

    Supervisors: Prof. Iryna Gurevych, Leonardo Filipe Rodrigues Ribeiro, M.Sc.

    Announcement as PDF

  • 2019/04/09

    Online learning for interactive annotation

    Master Thesis

    The goal of this thesis therefore is to research and evaluate online learning algorithms, i.e. algorithms that can be used to update models by only training on newly incoming data, reducing the need to retrain from scratch. go

    Supervisors: Prof. Iryna Gurevych, Jan-Christoph Klie, M.Sc.

    Announcement as PDF

  • 2019/03/22

    Investigating Style Transfer in Text Generation

    Bachelor Thesis, Master Thesis

    Supervisors: Prof. Iryna Gurevych, Dr. Gözde Gül (İşgüder) Şahin

    Announcement as PDF

  • 2019/01/08

    Developing an Inspector for Multilingual Word Representations

    Bachelor Thesis, Master Thesis

    Supervisors: Prof. Iryna Gurevych, Dr. Gözde Gül (İşgüder) Şahin

    Announcement as PDF

  • 2018/11/28

    Addressing The Speaker Consistency Issue in Conversational Agents

    Master Thesis

    Supervisors: Prof. Iryna Gurevych, Mohsen Mesgar, M.Sc.

    Announcement as PDF

  • 2018/03/01

    Using Coreference Resolution in Question Answering and How to Make the Best of It

    Master Thesis

    Coreference resolution is the task of finding different expressions that refer to the same entity. The availability of coreference information is beneficial for several applications including question answering. In this project, we want to examine the effect of state of the art supervised and unsupervised coreference resolvers in question answering systems by answering the following questions:

    How good should a coreference resolver be in order to improve the performance of a QA system?

    Due to the limited generalization of coreference resolvers, are unsupervised systems better suited for QA?

    Would it be more beneficial for QA if we customized coreference resolvers for only a subset of noun phrases (e.g. only resolving pronouns)? go

    Supervisors: Prof. Dr. Iryna Gurevych, Nafise Moosavi, M.Sc.

  • 2018/02/19

    VerbNet Semantic Role Labeling

    Master Thesis

    Semantic Role Labeling (SRL) automatically assigns labels to the participants of a situation described in a sentence. For example, given the sentence

    Bill hits a table with a hammer

    we want to discover that “Bill” is the Agent, “table” is the Theme and “hammer” is the Instrument of the action. Whereas FrameNet- and PropBank-based SRL has received significant attention, almost no work has been done on VerbNet-based SRL, which is more linguistically involved, but also more theoretically motivated and language-independent. Our hypothesis is that using additional constraints from semantic role theory can improve the performance of SRL systems, which can be then used as a preprocessing step for question answering, machine translation and other tasks. go

    Supervisors: Prof. Dr. Iryna Gurevych, Ilia Kuznetsov, Dipl.-Ling.

    Announcement as PDF

  • 2018/02/19

    Text Analytics using Supervised Text Classification

    Bachelor Thesis, Master Thesis

    Text classification has become a popular solution to many problems brought forward by social media platforms such as Twitter. In a nutshell, supervised text classification extracts relevant information from manually classified documents and learns a model from the extracted information. The growing text analytics market heavily relies on text classification to offer services such as sentiment analysis, document categorization, scientific discovery etc. With the help of DKPro-TC, our framework for supervised text classification, you will study novel text analysis tasks and collect new insights into artificial intelligence. go

    Supervisors: Prof. Dr. Iryna Gurevych, Dr.-Ing. Johannes Daxenberger

    Announcement as PDF

  • 2018/02/19

    Non-Factoid Question Answering

    Bachelor Thesis, Master Thesis

    Automatic Question Answering (QA) is a broad research area with the ultimate goal of finding useful answers for arbitrary questions. An important challenge in QA is finding answers for complicated questions that require expert knowledge, past experience, or opinions. Even though knowledge graphs contain huge amounts of factual information, they cannot be used to answer such complicated questions. We therefore explore innovative approaches to search for relevant, complex, and unstructured information within the large number of discussions in community Question Answering platforms such as StackExchange and Quora. go

    Supervisors: Prof. Dr. Iryna Gurevych, Andreas Rücklé, M.Sc.

    Announcement as PDF

  • 2018/02/19

    Natural Language Generation

    Bachelor Thesis, Master Thesis

    In the past few decades we have witnessed a fast growth of information content in all types of mass media. As the volume of published data grows, accessing and processing information in the shortest possible time is becoming of vital importance. Natural Language Generation (NLG) is the process of mapping from some underlying representation of information to a presentation of that information in an easily accessible textual or spoken form. NLG application spectrum includes question answering and recommendation systems, personalized assistants and human-computer interfaces, document summarizers and news generation machines. The goal of this thesis is to develop novel NLG approaches, design accurate evaluation methods and use NLG techniques for solving real-world problems. go

    Supervisors: Prof. Dr. Iryna Gurevych, Yevgeniy Puzikov, M.Sc.

    Announcement as PDF

  • 2018/02/19

    Leveraging User Interactions for Evidence Detection

    Bachelor Thesis, Master Thesis

    Current Evidence Detection (ED) techniques rely on machine learning methods that are trained once with a fixed corpus of specific hypotheses or topics. However, in common research activities (e.g. in historical research) hypotheses change over time requiring the model to continuously adapt to the specific needs of the user. This thesis focuses on the investigation of novel interactive machine learning methods to improve their capability to find evidences by leveraging user’s interaction data. The interaction logs collected in previous work will serve as a foundation for the development and evaluation of these methods. go

    Supervisors: Prof. Dr. Iryna Gurevych, Chris Stahlhut, M.Sc.

    Announcement as PDF

  • 2018/02/19

    Interpreting Deep Learning in NLP

    Master Thesis

    Deep neural networks are black-boxes – they take some input and produce an output using mathematical functions that are not interpretable to humans. This poses a problem in many domains, including NLP, where users would benefit from explanations relating input and output in a human-understandable form. Rules of the form “if input-characteristic-x and input-characteristic-y then output-value” can provide an explanation. Recently, methods for extracting such rules from deep neural networks have been developed. How to apply these methods to natural language data, e.g. word embeddings, is an open problem. go

    Supervisors: Prof. Dr. techn. Johannes Fürnkranz, Prof. Dr. Iryna Gurevych

    Announcement as PDF

  • 2018/02/19

    A Framework for Summarization Evaluation

    Bachelor Thesis, Master Thesis

    The evaluation of automatic summarization methods have so far heavily relied on comparing manually created reference summaries to the automatic ones. One standard method is ROUGE, of which an implementation is commonly used in summarization tasks. Another method is PYRAMID. But so far this has only been a manual evaluation technique and still relies on reference summaries. Recently, there have been attempts to automatically evaluate summaries without references. Others used and tested the Jensen-Shannon divergence and the Kullback-Leibler divergence of distributions extensively, varying the parameters of this approach. But so far there is no implementation of this method available. go

    Supervisor: Prof. Dr. Iryna Gurevych

  • 2018/02/19

    Deep Learning with External Memory

    Master Thesis

    Can you read a short story and answer questions about its contents afterwards? Most likely. Can neural networks do the same? Not quite. Most of today’s neural networks can handle a large number of individual sentences, but have trouble with full stories or books. Memory-augmented neural networks contain an external memory component which can store, retrieve and modify large amounts of data. This makes them a perfect fit for understanding stories or other machine comprehension tasks. go

    Supervisors: Prof. Dr. Iryna Gurevych, Michael Bugert, M.Sc.

    Announcement as PDF

  • 2018/02/19

    Active Deep Learning for Natural Language Processing

    Bachelor Thesis, Master Thesis

    Recently, deep learning gained much popularity. However, deep learning methods suffer from data sparsity – especially in NLP, where data is often cost-intensive to label. While active incremental learning approaches cope with this, they are not very well explored for deep learning models and most previous work has been done on convolutional neural networks for computer vision tasks. Furthermore, there is still only little support for such methods in the most common deep learning libraries.

    The goal of this thesis is to develop an active learning extension for a popular deep learning framework, such as PyTorch or Tensorflow, and compare different strategies for a natural language learning task. go

    Supervisors: Prof. Dr. Iryna Gurevych, Ji-Ung Lee, M.Sc.

    Announcement as PDF