Refine
Year of publication
Document Type
- Conference Proceeding (20)
- Article (6)
- Part of a Book (6)
- Master's Thesis (3)
- Doctoral Thesis (1)
Has Fulltext
- yes (36)
Is part of the Bibliography
- no (36) (remove)
Keywords
- Computerlinguistik (36) (remove)
Publicationstate
- Zweitveröffentlichung (36) (remove)
Reviewstate
Publisher
- Gesellschaft für Informatik e.V. (3)
- Narr (3)
- Association for Computing Machinery (2)
- European Language Resources Association (2)
- Libri Books on Demand (2)
- ACTA Press (1)
- Asian Federation of Natural Language Processing (1)
- Association for Computational Linguistics (1)
- Bibliographisches Institut (1)
- Deutscher Universitätsverlag (1)
The availability of electronic corpora of historical stages of languages has been wel- comed as possibly attenuating the inherent problem of diachronic linguistics, i.e. that we only have access to what has chanced to come down to us - the problem which was memorably named by Labov (1992) as one of “Bad Data”. However, such corpora can only give us access to an increased amount ot historical material and this can essentially still only be a partial and possibly distorted picture of the actual language at a particular period of history. Corpora can be improved by taking a more representative sample of extant texts if these are available (as they are in significant number for periods after the invention of printing). But, as examples from the recently compiled GerManC corpus of seventeenth and eighteenth century German show, the evidence from such corpora can still fail to yield definitive answers to our questions about earlier stages of a language. The data still require expert interpretation, and it is important to be realistic about what can legitimately be expected from an electronic historical corpus.
Automatic summarization systems usually are trained and evaluated in a particular domain with fixed data sets. When such a system is to be applied to slightly different input, labor- and cost-intensive annotations have to be created to retrain the system. We deal with this problem by providing users with a GUI which allows them to correct automatically produced imperfect summaries. The corrected summary in turn is added to the pool of training data. The performance of the system is expected to improve as it adapts to the new domain.
In this paper we present work in developing a computerized grammar for the Latin language. It demonstrates the principles and challenges in developing a grammar for a natural language in a modern grammar formalism. The grammar presented here provides a useful resource for natural language processing applications in different fields. It can be easily adopted for language learning and use in language technology for Cultural Heritage like translation applications or to support post-correction of document digitization.
We present a supervised machine learning AND system which tackles semantic similarity between publication titles by means of word embeddings. Word embeddings are integrated as external components, which keeps the model small and efficient, while allowing for easy extensibility and domain adaptation. Initial experiments show that word embeddings can improve the Recall and F score of the binary classification sub-task of AND. Results for the clustering sub-task are less clear, but also promising and overall show the feasibility of the approach.
In this contribution we present some work of the R&D European project “LIRICS” and of the ISO/TC 37/SC 4 committee related to the topic of interoperability and re-use of language resources. We introduce some basic mechanisms of the standardization work in ISO and describe in more details the general approach on how to cope with the annotation of language data within ISO.
Mehrsprachigkeit in linguistischen Daten. Theoretische und praktische Aspekte ihrer Erfassung
(2008)
Sentiment Analysis is the task of extracting and classifying opinionated content in natural language texts. Common subtasks are the distinction between opinionated and factual texts, the classification of polarity in opinionated texts, and the extraction of the participating entities of an opinion(-event), i.e. the source from which an opinion emanates and the target towards which it is directed. With the emerging Web 2.0 which describes the shift towards a highly user-interactive communication medium, the amount of subjective content on the World Wide Web is steadily increasing. Thus, there is a growing need for automatically processing this type of content which is provided by sentiment analysis. Both natural language processing, which is the task of providing computational methods for the analysis and representation of natural language, and machine learning, which is the task of building task-specific classification models on the basis of empirical data, may be instrumental in mastering the challenges of the automatic sentiment analysis of written text. Many problems in sentiment analysis have been proposed to be solved with machine learning methods exclusively using a fairly low-level feature design, such as bag of words, containing little linguistic information. In this thesis, we examine the effectiveness of linguistic features in various subtasks of sentiment analysis. Thus, we heavily draw from the insights gained by natural language processing. The application of linguistic features can be applied on various classification methods, be it in rule-based classification, where the linguistic features are directly encoded as a classifier, in supervised machine learning, where these features complement basic low-level features, or in bootstrapping methods, where these features form a rule-based classifier generating a labeled training set from which a supervised classifier can be trained. In this thesis, we will in particular focus on scenarios where the combination of linguistic features and machine learning methods is effective. We will look at common text classification tasks, both coarse-grained and fine-grained, and extraction tasks.
While good results have been achieved for named entity recognition (NER) in supervised settings, it remains a problem that for low resource languages and less studied domains little or no labelled data is available. As NER is a crucial preprocessing step for many natural language processing tasks, finding a way to overcome this deficit in data remains of great interest. We propose a distant supervision approach to NER that is both language and domain independent where we automatically generate labelled training data using gazetteers that we previously extracted from Wikipedia. We test our approach on English, German and Estonian data sets and contribute further by introducing several successful methods to reduce the noise in the generated training data. The tested models beat baseline systems and our results show that distant supervision can be a promising approach for NER when no labelled data is available. For the English model we also show that the distant supervision model is better at generalizing within the same domain of news texts by comparing it against a supervised model on a different test set.
Opinion holder extraction is one of the most important tasks in sentiment analysis. We will briefly outline the importance of predicates for this task and categorize them according to part of speech and according to which semantic role they select for the opinion holder. For many languages there do not exist semantic resources from which such predicates can be easily extracted. Therefore, we present alternative corpus-based methods to gain such predicates automatically, including the usage of prototypical opinion holders, i.e. common nouns, denoting for example experts or analysts, which describe particular groups of people whose profession or occupation is to form and express opinions towards specific items.
In der natürlichen Sprachverarbeitung haben Frage-Antwort-Systeme in der letzten Dekade stark an Bedeutung gewonnen. Vor allem durch robuste Werkzeuge wie statistische Syntax-Parser und Eigennamenerkenner ist es möglich geworden, linguistisch strukturierte Informationen aus unannotierten Textkorpora zu gewinnen. Zusätzlich werden durch die Text REtrieval Conference (TREC) jährlich Maßstäbe für allgemeine domänen-unabhängige Frage-Antwort-Szenarien definiert. In der Regel funktionieren Frage-Antwort-Systeme nur gut, wenn sie robuste Verfahren für die unterschiedlichen Fragetypen, die in einer Fragemenge vorkommen, implementieren. Ein charakteristischer Fragetyp sind die sogenannten Ereignisfragen. Obwohl Ereignisse schon seit Mitte des vorigen Jahrhunderts in der theoretischen Linguistik, vor allem in der Satzsemantik, Gegenstand intensive Forschung sind, so blieben sie bislang im Bezug auf Frage-Antwort-Systeme weitgehend unerforscht. Deshalb widmet sich diese Diplomarbeit diesem Problem. Ziel dieser Arbeit ist zum Einen eine Charakterisierung von Ereignisstruktur in Frage-Antwort Systemen, die unter Berücksichtigung der theoretischen Linguistik sowie einer Analyse der TREC 2005 Fragemenge entstehen soll. Zum Anderen soll ein Ereignis-basiertes Antwort-Extraktionsverfahren entworfen und implementiert werden, das sich auf den Ergebnissen dieser Analyse stützt. Informationen von diversen linguistischen Ebenen sollen daten-getrieben in einem uniformen Modell integriert werden. Spezielle linguistische Ressourcen, wie z.B. WordNet und Subkategorisierungslexika werden dabei eine zentrale Rolle einnehmen. Ferner soll eine Ereignisstruktur vorgestellt werden, die das Abpassen von Ereignissen unabhängig davon, ob sie von Vollverben oder Nominalisierungen evoziert werden, erlaubt. Mit der Implementierung eines Ereignis-basierten Antwort-Extraktionsmoduls soll letztendlich auch die Frage beantwortet werden, ob eine explizite Ereignismodellierung die Performanz eines Frage-Antwort-Systems verbessern kann.
We explore the feasibility of contextual healthiness classification of food items. We present a detailed analysis of the linguistic phenomena that need to be taken into consideration for this task based on a specially annotated corpus extracted from web forum entries. For automatic classification, we compare a supervised classifier and rule-based classification. Beyond linguistically motivated features that include sentiment information we also consider the prior healthiness of food items.
One problem of data-driven answer extraction in open-domain factoid question answering is that the class distribution of labeled training data is fairly imbalanced. In an ordinary training set, there are far more incorrect answers than correct answers. The class-imbalance is, thus, inherent to the classification task. It has a deteriorating effect on the performance of classifiers trained by standard machine learning algorithms. They usually have a heavy bias towards the majority class, i.e. the class which occurs most often in the training set. In this paper, we propose a method to tackle class imbalance by applying some form of cost-sensitive learning which is preferable to sampling. We present a simple but effective way of estimating the misclassification costs on the basis of class distribution. This approach offers three benefits. Firstly, it maintains the distribution of the classes of the labeled training data. Secondly, this form of meta-learning can be applied to a wide range of common learning algorithms. Thirdly, this approach can be easily implemented with the help of state-of-the-art machine learning software.
In recent years, text classification in sentiment analysis has mostly focused on two types of classification, the distinction between objective and subjective text, i.e. subjectivity detection, and the distinction between positive and negative subjective text, i.e. polarity classification. So far, there has been little work examining the distinction between definite polar subjectivity and indefinite polar subjectivity. While the former are utterances which can be categorized as either positive or negative, the latter cannot be categorized as either of these two categories. This paper presents a small set of domain independent features to detect indefinite polar sentences. The features reflect the linguistic structure underlying these types of utterances. We give evidence for the effectiveness of these features by incorporating them into an unsupervised rule-based classifier for sentence-level analysis and compare its performance with supervised machine learning classifiers, i.e. Support Vector Machines (SVMs) and Nearest Neighbor Classifier (kNN). The data used for the experiments are web-reviews collected from three different domains.
In this paper, we investigate the role of predicates in opinion holder extraction. We will examine the shape of these predicates, investigate what relationship they bear towards opinion holders, determine what resources are potentially useful for acquiring them, and point out limitations of an opinion holder extraction system based on these predicates. For this study, we will carry out an evaluation on a corpus annotated with opinion holders. Our insights are, in particular, important for situations in which no labelled training data are available and only rule-based methods can be applied.
In this paper, we compare three different generalization methods for in-domain and cross-domain opinion holder extraction being simple unsupervised word clustering, an induction method inspired by distant supervision and the usage of lexical resources. The generalization methods are incorporated into diverse classifiers. We show that generalization causes significant improvements and that the impact of improvement depends on the type of classifier and on how much training and test data differ from each other. We also address the less common case of opinion holders being realized in patient position and suggest approaches including a novel (linguistically-informed) extraction method how to detect those opinion holders without labeled training data as standard datasets contain too few instances of this type.
We present the German Sentiment Analysis Shared Task (GESTALT) which consists of two main tasks: Source, Subjective Expression and Target Extraction from Political Speeches (STEPS) and Subjective Phrase and Aspect Extraction from Product Reviews (StAR). Both tasks focused on fine-grained sentiment analysis, extracting aspects and targets with their associated subjective expressions in the German language. STEPS focused on political discussions from a corpus of speeches in the Swiss parliament. StAR fostered the analysis of product reviews as they are available from the website Amazon.de. Each shared task led to one participating submission, providing baselines for future editions of this task and highlighting specific challenges. The shared task homepage can be found at https://sites.google.com/site/iggsasharedtask/.
We present an experimental approach to determining natural dimensions of story comparison. The results show that untrained test subjects generally do not privilege structural information. When asked to justify sameness ratings, they may refer to content, but when asked to state differences, they mostly refer to style, concrete events, details and motifs. We conclude that adequate formal models of narratives must represent such non-structural data.
From Proof Texts to Logic. Discourse Representation Structures for Proof Texts in Mathematics
(2009)
We present an extension to Discourse Representation Theory that can be used to analyze mathematical texts written in the commonly used semi-formal language of mathematics (or at least a subset of it). Moreover, we describe an algorithm that can be used to check the resulting Proof Representation Structures for their logical validity and adequacy as a proof.
A formal narrative representation is a procedure assigning a formal description to a natural language narrative. One of the goals of the computational models of narrative community is to understand this procedure better in order to automatize it. A formal framework fit for automatization should allow for objective and reproducible representations. In this paper, we present empirical work focussing on objectivity and reproducibility of the formal framework by Vladimir Propp (1928). The experiments consider Propp’s formalization of Russian fairy tales and formalizations done by test subjects in the same formal framework; the data show that some features of Propp’s system such as the assignment of the characters to the dramatis personae and some of the functions are not easy to reproduce.
FnhdC/HTML und FnhdC/S
(2007)
Dieser Beitrag skizziert die Möglichkeiten, die die Extensible Markup Language (XML) im Umfeld von eLearning und Web Based Training (WBT) eröffnet. Bisherige eLearning-Angebote kranken an verschiedenen Problemen, die durch die Verwendung von XML-basierten Learning Objects vermieden werden können. Ausgehend vom aktuellen Stand im Projekt MiLCA - Medienintensive Lehrmodule in der Computerlinguistik-Ausbildung - soll zudem ein Ausblick auf zukünftige technische Möglichkeiten des Computer-gestützten Lernens gegeben werden.
The paper investigates the evolution of document grammars from a linguistic point of view. Document grammars have been developed in the past decades in order to formalize knowledge on the structure of textual information. A well-known instance of a document grammar is the »Document Type Definition« (DTD) as part of the Extensible Markup Language (XML). DTDs allow to define so-called tree grammars that constrain the application of tag-sets in the process of annotation of a document. In an XML-based document workflow, DTDs play a crucial role for validation and transforming huge amounts of texts in standardized data formats. An interesting point in the development of XML DTDs is the fact that the restriction of the formal expressiveness paved the way to understand the formal properties of document grammars better and to develop more a powerful version like XML Schema recently. In this sense, the simplicity of the original approach, resulting from the necessary restriction of previous approaches, yielded new complexity on formally understood grounds.
Sprachverarbeitung mit getypten Attribut-Wert-Matrizen. Dependenzgrammatik und Konzeptuelle Semantik
(1996)
In dieser Arbeit wurden die Dependenzgrammatik und die Konzeptuelle Semantik formalisiert. Als Ausgangspunkt dafür diente eine detaillierte Darstellung der formalen Grundlage. Diese wurden im Kapitel 1 erarbeitet. Nicht alle in diesem Kapitel entwickelten Konzepte wurden in den späteren Kapiteln aufgegriffen. Ich halte es aber für sinnvoll die mathematischen Eigenschaften eines Formalismus ausführlich darzustellen, bevor dieser zur Anwendung gebracht wird. Die beschriebenen Eigenschaften sind dem Formalismus immanent. Auf die Einführung von Erweiterungen, z.B. die Definition von Mengen, wurde verzichtet, da sie im weiteren Verlauf keine Verwendung finden.
Im Kapitel 2 wird gezeigt, dass die Dependenzgrammatik mit dem dargestellten Formalismus beschrieben werden kann. Damit wurde eine Formalisierung erreicht, die zeigt, dass der seltene Einsatz dieser traditionsreichen Grammatiktheorie in der Computerlinguistik, zumindest aus formalen Gründen, nicht gerechtfertigt ist.
Das Kapitel 3 stellt die Konzeptuelle Semantik vor. Die ursprüngliche Formalisierung dieser Theorie wurde kritisiert. Es wurde gezeigt, dass die Beschreibung der Konzepte durch getypte Attribut-Wert-Matrizen eine bessere Alternative der formalen Darstellung ist. Desweiteren wurden einerseits Vereinfachungen (z.B. der Verzicht auf die Dekomposition der Konzepte) und andererseits Erweiterungen (d.h. insbesondere eine Erweiterung des Inventars der ontologischen Kategorien) vorgeschlagen.
Nachdem diese beiden linguistischen Theorien mit demselben formalen Apparat dargestellt wurden, wurde im Kapitel 4 dargestellt, dass sie sich ergänzen. In dem skizzierten Sprachverarbeitungssystem werden die syntaktische und die semantische Struktur parallel aufgebaut. Es ist erkennbar, dass sich beide Theorien ergänzen. Es wurde darüber hinaus gezeigt, dass ein solches System eine sehr gut geeignete Basis zur maschinellen Verarbeitung defizitärer sprachlicher Äußerungen bildet.
Im Folgenden wird eine texttechnologische Komponente zur Expansion eines XML- annotierten Stammformenlexikons, das auf Einträgen eines Standardwörterbuchs basiert, vorgestellt. Diese Expansion wurde in der Document Style Semantics and Specification Language implementiert. Ihr Ergebnis ist ein Vollformenlexikon, das ebenfalls in XML repräsentiert ist.