Computerlinguistik
Refine
Document Type
- Conference Proceeding (3)
- Article (2)
- Part of a Book (2)
Has Fulltext
- yes (7)
Keywords
- Korpus <Linguistik> (4)
- Computerlinguistik (3)
- Deutsch (2)
- Englisch (2)
- Annotation (1)
- Automatische Sprachanalyse (1)
- Conversation analysis (1)
- Corpus linguistics (1)
- Corpus-based retrieval (1)
- Digitalisierung (1)
Publicationstate
- Veröffentlichungsversion (4)
- Postprint (3)
Reviewstate
- Peer-review (7) (remove)
Publisher
Question Answering Systems for retrieving information from Knowledge Graphs (KG) have become a major area of interest in recent years. Current systems search for words and entities but cannot search for grammatical phenomena. The purpose of this paper is to present our research on developing a QA System that answers natural language questions about German grammar.
Our goal is to build a KG which contains facts and rules about German grammar, and is also able to answer specific questions about a concrete grammatical issue. An overview of the current research in the topic of QA systems and ontology design is given and we show how we plan to construct the KG by integrating the data in the grammatical information system Grammis, hosted by the Leibniz-Institut für Deutsche Sprache (IDS). In this paper, we describe the construction of the initial KG, sketch our resulting graph, and demonstrate the effectiveness of such an approach. A grammar correction component will be part of a later stage. The paper concludes with the potential areas for future research.
Catching the common cause: extraction and annotation of causal relations and their participants
(2017)
In this paper, we present a simple, yet effective method for the automatic identification and extraction of causal relations from text, based on a large English-German parallel corpus. The goal of this effort is to create a lexical resource for German causal relations. The resource will consist of a lexicon that describes constructions that trigger causality as well as the participants of the causal event, and will be augmented by a corpus with annotated instances for each entry, that can be used as training data to develop a system for automatic classification of causal relations. Focusing on verbs, our method harvested a set of 100 different lexical triggers of causality, including support verb constructions. At the moment, our corpus includes over 1,000 annotated instances. The lexicon and the annotated data will be made available to the research community.
Feedback utterances are among the most frequent in dialogue. Feedback is also a crucial aspect of linguistic theories that take social interaction, involving language, into account. This paper introduces the corpora and datasets of a project scrutinizing this kind of feedback utterances in French. We present the genesis of the corpora (for a total of about 16 hours of transcribed and phone force-aligned speech) involved in the project. We introduce the resulting datasets and discuss how they are being used in on-going work with focus on the form-function relationship of conversational feedback. All the corpora created and the datasets produced in the framework of this project will be made available for research purposes.
Ein integriertes Datenbank-, Such- und Tagging-Tool (IDaSTo) wird vorgestellt, das sich besonders für Variablenanalysen, für Paralleltexte und für diachronische Untersuchungen eignet. Relevante Kategorien bzw. Variablen können individuell definiert, Tags frei im Text und auf verschiedenen Wegen gesetzt und ihre Häufigkeiten in den verlinkten Statistiken direkt abgerufen werden.
When a noise verb is used to indicate verbal communication, factors from both the source domain of the verb (perception) and the target domain (communication) play a role in determining the argument structure of the sentence. While the target domain supplies a syntactic structure, the source domain’s semantics constrain the degree to which that syntactic structure can be exploited. This can be determined by comparing noise verbs in this use with manner-of-communication verbs, which are superficially similar, but native to communication. Data for these two classes of verbs were drawn from the British National Corpus. The data were annotated with frame-semantic markup, as described in the Berkeley FrameNet Project. We compared the presence, type of syntactic realization, and position of the semantically annotated arguments for both classes of verbs. We found that noise and manner verbs show statistically significant differences in these three areas. For instance, noise verbs are more focused on the form of the message than manner verbs: noise verbs appear more frequently with a quoted message. In addition, there are differences other than the complementation patterns: certain noise verbs are biased with respect to speakers’ genders, message types, and even orthography in quoted messages
As the nature of negative polarity items (NPIs) and their licensing contexts is still under much debate, a broad empirical basis is an important cornerstone to support further insights in this area of research. The work discussed in this paper is intended as a contribution to realizing this objective. The authors briefly introduce the phenomenon of NPIs and outline major theories about their licensing and also various licensing contexts before discussing our major topics: Firstly, a corpus-based retrieval method for NPI candidates is described that ranks the candidates according to their distributional dependence on the licensing contexts. Our method extracts single-word candidates and is extended to also capture multi-word candidates. The basic idea for automatically collecting NPI candidates from a large corpus is that an NPI behaves like a kind of collocate to its licensing contexts. Manual inspection and interpretation of the candidate lists identify the actual NPIs. Secondly, an online repository for NPIs and other items that show distributional idiosyncrasies is presented, which offers an empirical database for further (theoretical) research on these items in a sustainable way.
Der Beitrag behandelt konzeptionelle und methodische Fragen aus einem Projekt, in dem eine neue Referenzausgabe des Thomas Mannschen Gesamtwerks für die Publikation in zwei Medien aufbereitet wird: als Buch und als elektronische Ausgabe. Die Basis dafür bildet ein Informationspool, in dem die Texte SGML/XML-basiert vorgehalten und durch eine Topic Map verknüpft werden. Der Beitrag skizziert die Architektur des Systems sowie die dahinter stehenden technischen und konzeptionellen Überlegungen. Es wird gezeigt, wie gerade die elektronische Version neue Wege beschreitet, damit ein Arbeitswerkzeug für Literaturwissenschaftler entsteht, das völlig neuartige Zugriffsmöglichkeiten auf das Werk Thomas Manns bietet.