Data Mining Practical Machine Learning Tools and Techniques

https://leseprobe.buch.de/images-adb/a8/ce/a8ce578b-41ae-4377-b869-b8993abcf1f3.pdf

Lexikon der Sprachwissenschaft

A NEW book by Mr. Udny Yule is a statistical event which, though of great rarity, is all the more welcome when it occurs. This, however, is not a formal treatment of a subject which has already shaken down into definite lines of development, or even a systematic introduction to such a subject. Rather is it an account in volume form of Mr. Yule's incursion into a novel and interesting field of research. The Statistical Study of Literary Vocabulary By G. Udny Yule. Pp. ix + 306. (Cambridge: At the University Press, 1944.) 25s. net.

The Statistical Study of Literary Vocabulary

Contextualized word embeddings (CWE) such as provided by ELMo (Peters et al., 2018), Flair NLP (Akbik et al., 2018), or BERT (Devlin et al., 2019) are a major recent innovation in NLP. CWEs provide semantic vector representations of words depending on their respective context. Their advantage over static word embeddings has been shown for a number of tasks, such as text classification, sequence tagging, or machine translation. Since vectors of the same word type can vary depending on the respective context, they implicitly provide a model for word sense disambiguation (WSD). We introduce a simple but effective approach to WSD using a nearest neighbor classification on CWEs. We compare the performance of different CWE models for the task and can report improvements above the current state of the art for two standard WSD benchmark datasets. We further show that the pre-trained BERT model is able to place polysemic words into distinct 'sense' regions of the embedding space, while ELMo and Flair NLP do not seem to possess this ability.

Does BERT Make Any Sense? Interpretable Word Sense Disambiguation with Contextualized Embeddings

This paper describes development and design of an ontology of linguistic annotations, primarily word classes and morphosyntactic features, based on existing standardization approaches (e.g. EAGLES), a set of annotation schemes (e.g. for German, STTS and morphological annotations), and existing terminological resources (e.g. GOLD). The ontology is intended to be a platform for terminological integration, integrated representation and ontology-based search across existing linguistic resources with terminologically heterogeneous annotations. Further, it can be applied to augment the semantic analysis of a given text with an ontological interpretation of its morphosyntactic analysis.

An ontology of linguistic annotations

Linguistic query systems are special purpose IR applications. As text sizes, annotation layers, and metadata schemes of language corpora grow rapidly, performing complex searches becomes a highly computational expensive task. We evaluate several storage models and indexing variants in two multi-processor/multi-core environments, focusing on prototypical linguistic querying scenarios. Our aim is to reveal modeling and querying tendencies – rather than absolute benchmark results – when using a relational database management system (RDBMS) and MapReduce for natural language corpus retrieval. Based on these findings, we are going to improve our approach for the efficient exploitation of very large corpora, combining advantages of state-of-the-art database systems with decomposition/parallelization strategies. Our reference implementation uses the German DeReKo reference corpus with currently more than 4 billion word forms, various multi-layer linguistic annotations, and several types of text-specific metadata. The proposed strategy is language-independent and adaptable to large-scale multilingual corpora.

/pdf/evaluating-dbms-based-access-strategies-to-very-large-multi-1tqwqcbst5.pdf

Evaluating DBMS-based Access Strategies to Very Large Multi-layer Corpora

Song lyrics can be considered as a text genre that has features of both written and spoken discourse, and potentially provides extensive linguistic and cultural information to scientists from various disciplines. However, pop songs play a rather subordinate role in empirical language research so far - most likely due to the absence of scientifically valid and sustainable resources. The present paper introduces a multiply annotated corpus of German lyrics as a publicly available basis for multidisciplinary research. The resource contains three types of data for the investigation and evaluation of quite distinct phenomena: TEI-compliant song lyrics as primary data, linguistically and literary motivated annotations, and extralinguistic metadata. It promotes empirically/statistically grounded analyses of genre-specific features, systemic-structural correlations and tendencies in the texts of contemporary pop music. The corpus has been stratified into thematic and author-specific archives; the paper presents some basic descriptive statistics, as well as the public online frontend with its built-in evaluation forms and live visualisations.

A Corpus Linguistic Perspective on Contemporary German Pop Lyrics with the Multi-Layer Annotated "Songkorpus".

Contemporary studies on the characteristics of natural language benefit enormously from the increasing amount of linguistic corpora. Aside from text and speech corpora, corpora of computer-mediated communication (CMC) position themselves between orality and literacy, and beyond that provide insight into the impact of “new”, mainly internet-based media on language behaviour. In this paper, we present an empirical attempt to work with annotated CMC corpora for the explanation of linguistic phenomena. In concrete terms, we implement machine learning algorithms to produce decision trees that reveal rules and tendencies about the use of genitive markers in German.

Decision Tree-Based Evaluation of Genitive Classification – An Empirical Study on CMC and Text Corpora

Das Online-Wortschatz-Informationssystem Deutsch (OWID) ist ein digitales Worterbuchportal des Instituts fur Deutsche Sprache. Alle darin zusammengefuhrten lexikografischen Daten sind auf XML-Basis feingranular strukturiert. Speicherung, Verwaltung und Retrieval dieser Daten ubernimmt das Orade-basierte Electronic Dictionary Administration System (EDAS). Der vorliegende Beitrag erlautert die XML-basierte Modellierung der Daten, XML-spezifische Fragen der Speicherung, sowie das Retrieval mit XPath und SQL/XML.

Ein XML-basiertes Datenbanksystem für digitale Wörterbücher- Ein Werkstattbericht aus dem Institut für Deutsche Sprache

/pdf/hypertext-wissensnetz-und-datenbank-die-2oze12ha2s.pdf

Roman Schneider

Papers

Evaluating DBMS-based Access Strategies to Very Large Multi-layer Corpora

A Corpus Linguistic Perspective on Contemporary German Pop Lyrics with the Multi-Layer Annotated "Songkorpus".

Decision Tree-Based Evaluation of Genitive Classification – An Empirical Study on CMC and Text Corpora

Ein XML-basiertes Datenbanksystem für digitale Wörterbücher- Ein Werkstattbericht aus dem Institut für Deutsche Sprache

Hypertext, Wissensnetz und Datenbank: die Webinformationssysteme Grammis und ProGr@mm