05 Fakultät Informatik, Elektrotechnik und Informationstechnik

Permanent URI for this collectionhttps://elib.uni-stuttgart.de/handle/11682/6

Browse

Filters

201821

Settings

Institute: search.filters.UBSInstitut.Institut für Maschinelle SprachverarbeitungStart date: 2018End date: 2018

Search Results

Now showing 1 - 10 of 21
  • Thumbnail Image
    ItemOpen Access
  • Thumbnail Image
    ItemOpen Access
    Modeling the position and inflection of verbs in English to German machine translation
    (2018) Ramm, Anita; Fraser, Alexander (Prof. Dr.)
  • Thumbnail Image
    ItemOpen Access
    Die Rolle von Abstraktheit und Wortbedeutungen bei der Unterscheidung von wörtlichen und nicht-wörtlichen Bedeutungen von deutschen Partikelverben
    (2018) Gemander, Jan
    Ziel dieser Arbeit ist es, die wörtliche bzw. metaphorische Verwendung von deutschen Partikelverben richtig identifizieren zu können. Als erster Schritt werden hier der von Köper und Schulte im Walde (2016) vorgeschlagene Klassifizierer in Python reimplementiert und die Menge der verwendeten Daten erweitert. Als zweiten zentralen Schritt dieser Arbeit variieren wir die verwendeten Abstraktheitsfeatures und experimentieren mit eigens erzeugten Werten. Als letztes Feature werfen wir einen Blick auf die Verwendung der Wortbedeutungen in Form der im Duden definierten Senses, welche wir mithilfe des Lesk-Algorithmus (Lesk, 1986) sowie Wortvektoren bestimmen.
  • Thumbnail Image
    ItemOpen Access
    A visual analytics approach for explainability of deep neural networks
    (2018) Kuznecov, Paul
    Deep Learning has advanced the state-of-the-art in many fields, including machine translation, where Neural Machine Translation (NMT) has become the dominant approach in recent years. However, NMT still faces many challenges such as domain adaption, over- and under-translation, and handling long sentences, making the need for human translators apparent. Additionally, NMT systems pose the problems of explainability, interpretability, and interaction with the user, creating a need for better analytics systems. This thesis introduces NMTVis, an integrated Visual Analytics system for NMT aimed at translators. The system supports users in multiple tasks during translation: finding, filtering and selecting machine-generated translations that possibly contain translation errors, interactive post-editing of machine translations, and domain adaption from user corrections to improve the NMT model. Multiple metrics are proposed as a proxy for translation quality to allow users to quickly find sentences for correction using a parallel coordinates plot. Interactive, dynamic graph visualizations are used to enable exploration and post-editing of translation hypotheses by visualizing beam search and attention weights generated by the NMT model. A web-based user study showed that a majority of participants rated the system positively regarding functional effectiveness, ease of interaction and intuitiveness of visualizations. The user study also revealed a preference for NMTVis over traditional text-based translation systems, especially for large documents. Additionally, automated experiments were conducted which showed that using the system can reduce post-editing effort and improve translation quality for domain-specific documents.
  • Thumbnail Image
    ItemOpen Access
    Detecting ambiguity in statutory texts
    (2018) Zeller, Tom
    Ambiguity is ever-present in natural language production. A human typically has no difficulties in selecting the right interpretation for an ambiguous expression by using lexical and pragmatic knowledge. While the inclusion of broad semantic knowledge poses a challenge for general disambiguation systems and parsers, its utilization might be a feasible approach for disambiguation in a restricted context. A domain that is very sensitive to ambiguity is the legal domain, especially in the wording of statutory text. Some parsing systems deal with ambiguous input by specifying all possible interpretations without explicitly choosing a solution or by returning multiple parses along with their respective probability. This work serves two purposes: An application is created which allows the input of statutory texts or single text excerpts and which detects included structural ambiguities in the form of prepositional phrase attachments and coordination ambiguities, and semantic ambiguity in the form of scopal ambiguity. Furthermore, the found ambiguities are filtered by including subcategorizational information and by utilizing domain-specific semantic knowledge which is encoded in the form of a legal domain ontology and selectional preferences for common legal expressions. The filtering capability and the effect of including the semantic knowledge are evaluated on the DUBLIN3 Regulation.
  • Thumbnail Image
    ItemOpen Access
    The Taming of the Shrew - non-standard text processing in the Digital Humanities
    (2018) Schulz, Sarah; Kuhn, Jonas (Prof. Dr.)
    Natural language processing (NLP) has focused on the automatic processing of newspaper texts for many years. With the growing importance of text analysis in various areas such as spoken language understanding, social media processing and the interpretation of text material from the humanities, techniques and methodologies have to be reviewed and redefined since so called non-standard texts pose challenges on the lexical and syntactic level especially for machine-learning-based approaches. Automatic processing tools developed on the basis of newspaper texts show a decreased performance for texts with divergent characteristics. Digital Humanities (DH) as a field that has risen to prominence in the last decades, holds a variety of examples for this kind of texts. Thus, the computational analysis of the relationships of Shakespeare’s dramatic characters requires the adjustment of processing tools to English texts from the 16th-century in dramatic form. Likewise, the investigation of narrative perspective in Goethe’s ballads calls for methods that can handle German verse from the 18th century. In this dissertation, we put forward a methodology for NLP in a DH environment. We investigate how an interdisciplinary context in combination with specific goals within projects influences the general NLP approach. We suggest thoughtful collaboration and increased attention to the easy applicability of resulting tools as a solution for differences in the store of knowledge between project partners. Projects in DH are not only constituted by the automatic processing of texts but are usually framed by the investigation of a research question from the humanities. As a consequence, time limitations complicate the successful implementation of analysis techniques especially since the diversity of texts impairs the transferability and reusability of tools beyond a specific project. We answer to this with modular and thus easily adjustable project workflows and system architectures. Several instances serve as examples for our methodology on different levels. We discuss modular architectures that balance time-saving solutions and problem-specific implementations on the example of automatic postcorrection of the output text from an optical character recognition system. We address the problem of data diversity and low resource situations by investigating different approaches towards non-standard text processing. We examine two main techniques: text normalization and tool adjustment. Text normalization aims at the transformation of non-standard text in order to assimilate it to the standard whereas tool adjustment concentrates on the contrary direction of enabling tools to successfully handle a specific kind of text. We focus on the task of part-of-speech tagging to illustrate various approaches toward the processing of historical texts as an instance for non-standard texts. We discuss how the level of deviation from a standard form influences the performance of different methods. Our approaches shed light on the importance of data quality and quantity and emphasize the indispensability of annotations for effective machine learning. In addition, we highlight the advantages of problem-driven approaches where the purpose of a tool is clearly formulated through the research question. Another significant finding to emerge from this work is a summary of the experiences and increased knowledge through collaborative projects between computer scientists and humanists. We reflect on various aspects of the elaboration and formalization of research questions in the DH and assess the limitations and possibilities of the computational modeling of humanistic research questions. An emphasis is placed on the interplay of expert knowledge with respect to a subject of investigation and the implementation of tools for that purpose and the thereof resulting advantages such as the targeted improvement of digital methods through purposeful manual correction and error analysis. We show obstacles and chances and give prospects and directions for future development in this realm of interdisciplinary research.
  • Thumbnail Image
    ItemOpen Access
    Computational approaches for German particle verbs: compositionality, sense discrimination and non-literal language
    (2018) Köper, Maximilian; Schulte im Walde, Sabine (PD Dr.)
    Anfangen (to start) is a German particle verb. Consisting of two parts, a base verb ("fangen") and particle ("an"), with potentially many or no intervening words in a sentence, particle verbs are highly frequent constructions with special properties. It has been shown that this type of verb represents a serious problem for language technology, due to particle verbs' ambiguity, ability to occur separate and seemingly unpredictable behaviour in terms of meaning. This dissertation addresses the meaning of German particle verbs via large-scale computational approaches. The three central parts of the thesis are concerned with computational models for the following components: i) compositionality, ii) senses and iii) non-literal language. In the first part of this thesis, we shed light on the phenomena by providing information on the properties of particle verbs, as well as the related and prior literature. In addition, we present the first corpus-driven statistical analysis. We use two different approaches for addressing the modelling of compositionality. For both approaches, we rely on large amounts of textual data with an algebraic model for representation to approximate meaning. We put forward the existing methodology and show that the prediction of compositionality can be improved by considering visual information. We model the particle verb senses based only on huge amounts of texts, without access to other resources. Furthermore, we compare and introduce the methods to find and represent different verb senses. Our findings indicate the usefulness of such sense-specific models. We successfully present the first model for detecting the non-literal language of particle verbs in a running text. Our approach reaches high performance by combining the established techniques from metaphor detection with particle verb-specific information. In the last part of the thesis, we approach the regularities and the meaning shift patterns. Here, we introduce a novel data collection approach for accessing the meaning components, as well as a computational model of particle verb analogy. The experiments reveal typical patterns in domain changes. Our data collection indicates that coherent verbs with the same meaning shift represent rather scarce phenomena. In summary, we provide novel computational models to previously unaddressed problems, and we report incremental improvements in the existing approaches. Across the models, we observe that semantically similar or synonymous base verbs behave similarly when combined with a particle. In addition, our models demonstrate the difficulty of particle verbs. Finally, our experiments suggest the usefulness of external normative emotion and affect ratings.
  • Thumbnail Image
    ItemOpen Access
    Investigating different levels of joining entity and relation classification
    (2018) Milovanovic, Milan
    Named entities, such as persons or locations, are crucial bearers of information within an unstructured text. Recognition and classification of these (named) entities is an essential part of information extraction. Relation classification, the process of categorizing semantic relations between two entities within a text, is another task closely linked to named entities. Those two tasks -- entity and relation classification -- have been commonly treated as a pipeline of two separate models. While this separation simplifies the problem, it also disregards underlying dependencies and connections between the two subtasks. As a consequence, merging both subtasks into one joint model for entity and relation classification is the next logical step. A thorough investigation and comparison of different levels of joining the two tasks is the goal of this thesis. This thesis will accomplish the objective by defining different levels of joint entity and relation classification and developing (implementing and evaluating) and analyzing machine learning models for each level. The levels which will be investigated are: (L1) a pipeline of independent models for entity classification and relation classification (L2) using the entity class predictions as features for relation classification (L3) global features for both entity and relation classification (L4) explicit utilization of a single joint model for entity and relation classification The best results are achieved using the model for level 3 with an F1 score of 0.830 for entity classification and an F_1 score of 0.52 for relation classification.
  • Thumbnail Image
    ItemOpen Access
    Neural-based methods for user simulation in dialog systems
    (2018) Schmidt, Maximilian
    Spoken Dialog Systems allow users to interact with a Dialog Manager (DM) using natural language, thereby following a goal to fulfill their task. State-of-the-art solutions cast the problem as Markov Decision Process, leveraging Reinforcement Learning (RL) algorithms to find an optimal dialog strategy for the DM. For this purpose, several thousand dialogs need to be seen by the RL agent. A user simulator comes in handy to generate responses on demand, however the current state-of-the-art agenda-based user simulators lack the ability to model real human subjects. In this thesis, this problem is addressed by implementing a user simulator using a Recurrent Neural Network which approximates the agenda-based model in a first step. Going onwards, it is shown to learn noise and variance treated as varying user behavior. This is used to train the simulator on real data thus modeling real users.
  • Thumbnail Image
    ItemOpen Access
    Using morpho-syntactic and semantic information to improve statistical machine translation
    (2018) Di Marco, Marion; Schulte im Walde, Sabine (PD Dr.)
    Statistische Maschinelle Übersetzungssystem werden von Wort-alignierten parallelen Corpora abgeleitet und benutzen üblicherweise keine expliziten linguistischen Informationen. Dies kann zu Generalisierungsproblemen führen, besonders wenn morphologisch komplexe Sprachen übersetzt werden. Diese Arbeit untersucht die Integration von linguistischen Informationen in ein Übersetzungssystem, das in eine morphologisch komplexe Sprache übersetzt: basierend auf einem Übersetzungssystem, das die Morphologie der Zielsprache modelliert, werden syntaktische und semantische Informationen in das System integriert, mit dem Ziel, die Modellierung von Subkategorisierung und Präpositionen zu verbessern.