Application Descriptions

Alpino is a dependency parser for Dutch, developed in the context of the PIONIER Project Algorithms for Linguistic Processing, developed by Gertjan van Noord at the University of Groningen. You can upload either tokenised or untokenised files (which will be automatically tokenised for you using ucto), the output will consist of a zip file containing XML files, one for each sentence in the input document.

Apache Stanbol provides a set of reusable components for semantic content management. A number of EnhancementEngines extract features from passed content, for details see https://stanbol.apache.org. The resulting RDF enhancements are returned in JSON format.

Colibri core is an NLP tool as well as a C++ and Python library for working with basic linguistic constructions such as n-grams and skipgrams (i.e patte rns with one or more gaps, either of fixed or dynamic size) in a quick and memory-efficient way.

Colibri core is an NLP tool as well as a C++ and Python library for working with basic linguistic constructions such as n-grams and skipgrams (i.e patterns with one or more gaps, either of fixed or dynamic size) in a quick and memory-efficient way.

The Collection Registry - serves as a catalog of collections which occurred within the scope of research projects or serves as a basis for them. - links data, whose data models and the description of a collection for technical reuse by services such as search or analysis tools. - also serves to manage collection descriptions. These can include, in addition to digitally accessible, analog, protected or offline collections.

		The purpose of the Collection Registry is
		- to describe distributed collections in one place and to process them together in other services (e.g. Generic search, Cosmotool).
		- to make collections visible in the Collection Registry, which are otherwise difficult to find.
		- to document own collections and make them demonstrable for other scientists.
		- in order to be able to manage relevant collections in the sense of an internal catalog.

Morphosyntactic tagger for Polish based on constrained conditional random fields. Part of: Multiservice, a robust linguistic Web service for Polish.

A statistical tool chain for performing Coreference Resolution. Part of: Multiservice, a robust linguistic Web service for Polish.

Java coreference-based summarization tool; its creation was cofunded by the European Union from resources of the European Social Fund -- Project PO KL 'Information technologies: Research and their interdisciplinary applications'. Part of: Multiservice, a robust linguistic Web service for Polish.

The Polish dependency parser is trained on the extended version of the Polish dependency treebank (Składnica zależnościowa) with the publicly available parsing systems – MaltParser or MateParser. MaltParser is a transition-based dependency parser that uses a deterministic parsing algorithm. The deterministic parsing algorithm builds a dependency structure of an input sentence based on transitions (shift-reduce actions) predicted by a classifier. The classifier learns to predict the next transition given training data and the parse history. MateParser, in turn, is a graph-based parser that defines a space of well-formed candidate dependency trees for an input sentence, scores them given an induced parsing model, and selects the highest scoring dependency tree as a correct analysis of the input sentence. Part of: Multiservice, a robust linguistic Web service for Polish.

Statistical named entity recognition tool based on linear-chain conditional random fields. Part of: Multiservice, a robust linguistic Web service for Polish.

A morphosyntactic tagger extended with a semantic category, expressing properties of positive or negative sentiment. Part of: Multiservice, a robust linguistic Web service for Polish.

Tool for partial parsing and rule-based morphosyntactic disambiguation. Part of: Multiservice, a robust linguistic Web service for Polish.

ConedaKOR facilitate the administration and presentation of academic collections of objects from the image-based cultural sciences and humanities. It allows to store arbitrary documents and interconnect them with relationships. You can build huge semantic networks for an unlimited amount of domains. ConedaKOR integrates a sophisticated ontology management tool with an easy-to-use media database.

COSMAS II is a database (Corpus Search, Management and Analysis System) designed at the IDS for corpus-based research on language

            - in extensive corpora (over 13 billion word forms, provided by the DEREKO project);
            - in linguistically and structurally annotated corpora; e.g. word classes (over 1.7 billion nouns), headings etc;
            - in user-defined corpus selections (based on up to eight bibliographic criteria);
            - in different language corpora with custom tag sets, useing an embedded graphical wizard;
            - using numerous search, distance and range operators that allow to formulate simple to complex facts or grammatical patterns.
            
            The results are 
            
            - summarized and sorted according to bibliographical criteria;
            - evaluated by frequency measures in terms of their distribution;
            - analysed, sorted and tabulated using a co-competition analysis;
            - sorted, analysed and presented as KWIC and supporting documents;
            - (if desired) reduced to a representative, manageable quantity by means of a random generator.

CosmoTool is a digital tool that combines biographical information from different sources into inter- and national movement profiles of historical personalities. This is intended to draw conclusions on characteristics and rules, which can be regarded as international criteria. CosmoTool is based on DARIAH-DE federation architecture and allows the extraction of data from unstructured text. At the moment, CosmoTool is in the development phase and still offers limited functionality.

This is an experimental integration of a D4Science NLP processing service (CSTLemma). The CSTLemma Lemmatizer for English reduces all words in a text to their base form, the lemma.

In a corpus-based empirical linguistic approach, it is of fundamental importance to conceive a methodology that is coherent in terms of scientific methodology and that makes it possible to systematically uncover, inventory, interpret and theoretically substantiate the emergent structures manifest in language use. As an empirical basis for this research project, a large collection of co-occurrence profiles for about 220,000 different lemmas was built up in the Programme Area Corpus Linguistics of the Leibniz Institute for the German Language based on a corpus of written contemporary language of about 2.2 billion running text words. For each lemma, the collection contains the results of up to five different co-occurrence analyses in the form of hierarchies of similar uses, with up to 100,000 examples of use per lemma and analysis.

            Guided by the explorative analysis of this language material, we strive to gain new insights into the structures, regularities, properties and functions of language. Currently we focus on topics such as similarity of coccurrence profiles and semantic proximity, on the interrelationships between local, lexical and global, situational contexts, and on various studies on quasi-synonymy.
            
            Through this website we would like to make parts of our thinking and experimenting platform in the sense of a "transparent laboratory" accessible to all interested colleagues.

This is an experimental integration of a D4Science NLP processing service (based on GATE's ANNIE). This service identifies names of persons, locations, organizations, as well as money amounts, time and date expressions in English texts automatically.

The DARIAH DKPro Wrapper is a wrapper for DKPro Core, a tool for linguistic annotation.

The DARIAH DKPro Wrapper is a wrapper for DKPro Core, a tool for linguistic annotation.

The DARIAH DKPro Wrapper is a wrapper for DKPro Core, a tool for linguistic annotation.

The DARIAH DKPro Wrapper is a wrapper for DKPro Core, a tool for linguistic annotation.

The DARIAH DKPro Wrapper is a wrapper for DKPro Core, a tool for linguistic annotation.

The DARIAH DKPro Wrapper is a wrapper for DKPro Core, a tool for linguistic annotation.

The DARIAH DKPro Wrapper is a wrapper for DKPro Core, a tool for linguistic annotation.

The DARIAH DKPro Wrapper is a wrapper for DKPro Core, a tool for linguistic annotation.

The DARIAH DKPro Wrapper is a wrapper for DKPro Core, a tool for linguistic annotation.

The DARIAH DKPro Wrapper is a wrapper for DKPro Core, a tool for linguistic annotation.

The DARIAH-DE Geo-Browser allows a comparative visualization of several requests and facilitates the representation of data and their visualization in a correlation of geographic spatial relations at corresponding points of time and sequences.

The entry point for importing collections and data into the DARIAH-DE Repository is the DARIAH-DE Publikator, which allows you to prepare, manage, and finally import your collections into the DARIAH-DE Repository using your favorite internet browser.

The Data Modeling Environment (DME) from DARIAH-DE is a tool for modeling and association of data. A key special feature of the DME is its research-oriented focus and the underlying concepts for the explication of domain knowledge.

The German Text Archive (DTA) is the largest single corpus of historical New High German covering the period from the 16th to the early 20th century, comprising more than 350 million tokens in 1.34 million digitized pages. Focusing mostly on (digitized) printed material, the DTA also includes a growing number of hand-written documents. Specialty sub-corpora include historical newspapers and other periodicals. The DTA as a whole covers a rich variety of fiction and non-fiction texts, the latter including academic as well as non-academic writing.

The DTA is composed of the so-called DTA-Kernkorpus (DTAK, “DTA Core Corpus”) with approximately 1500 first editions from the 16th through the 19th century. Additionally, the DTA-Erweiterungen (DTAE, “DTA Extensions”) module contains specialty corpora and individual texts which have been curated in the context of CLARIN-D and other projects. The full-text sources provided by digitization projects and other discipline-specific initiatives have been (manually or semi-automatically) converted to a TEI-compatible XML format conforming to the DTA-Basisformat (DTABf, “DTA Base Format”) guidelines, including extensive metadata on the original sources and data preparation. OCR texts in the DTA Core Corpus – as well as numerous additional text resources – have been manually corrected. A continuous quality assurance process is made possible by the collaborative web-based platform DTAQ, with around 2000 currently registered users. All DTA corpora are prepared for user consumption by automated computational linguistic analysis methods, including not only PoS-tagging and lemmatization, but also – among others – the orthographic normalization of historical spelling variants, allowing users to formulate queries in modern orthography.

Collaborative Quality Assurance in the German Text Archive (DTA) DTAQ (Deutsches Textarchiv - Qualitätssicherung) is a web-based application for finding, categorizing and correcting various types of errors in XML/TEI annotated texts. The interface of DTAQ can be individually adapted by each user, so that different views of the source digitized material and text transcriptions can be set.

DTAQ can be used freely by everyone after registration.

The DGD is the Database for Spoken German ("Datenbank für Gesprochenes Deutsch"). To use the DGD, you need to register (it's free). The DGD's user interface is in German. We are sorry we cannot provide a localized interface for other languages.

The DGD gives registered users access to 34 corpora of spoken language from the Archive for Spoken German ("Archiv für Gesprochenes Deutsch", AGD). The corpora comprise:

• The Research and Teaching Corpus of Spoken German ("Forschungs und Lehrkorpus Gesprochenes Deutsch", FOLK), a state-of-the-art corpus of spontenaous interaction data
• The GeWiss Corpus ("Gesprochene Wissenschaftssprache Kontrastiv") of academic speech
• Further interaction corpora, such as the Freiburger Korpus ("FR") and the corpus Dialogstrukturen ("DS")
• The large "historic" dialect corpora of German, most importantly the corpus German dialects ("Deutsche Mundarten", "Zwirner-Korpus", ZW) and its "satellite corpora" German dialects in Eastern Europe (OS), German dialects in the Black Forest region (SV), German dialects in south-west Germany (SW), German dialects in the GDR (DR)
• Other influential variation corpora for German, such as the corpus Basic German ("Deutsche Umgangssprachen", "Pfeffer-Korpus", PF) and the corpus Standard German ("Deutsche Standardsprache", "König-Korpus", KN), as well as the more recent corpus Deutsch Heute ("DH")
• Corpora on extra-territorial varieties of German ("speech islands") such as Michael Clyne's corpus on Australian German, a corpus on German in Russia, a corpus on German in Namibia and a corpus on Mennonite Low German in the Americas
• Anne Betten's corpora on the German of Emigrants to Israel ("Emigrantendeutsch in Israel", IS, ISW, ISZ)
• Norbert Dittmar's corpus on German reunification ("Berliner Wendekorpus", BW)

Altogether, the DGD contains more than 4,000 hours of audio and video recordings, and more than 12 million transcribed tokens. With a few exceptions, all transcriptions in the database are time-aligned with the recordings and annotated with lemma and part-of-speech information.

DiaCollo (pronounced /diːˈakəloʊ/, "dee-ah-kə-loh", analogous to the well-known juggling prop) is a tool for efficient extraction of diachronic collocations from an underlying text corpus. Unlike other collocation extractors such as DWDS Wortprofil, Sketch Engine, or the UCS toolkit, DiaCollo is suitable for extraction and analysis of diachronic collocation data, i.e. collocations whose significance depends on the date of their occurrence. By tracking changes in a word's typical collocates over time and applying J. R. Firth's famous principle that "you shall know a word by the company it keeps", DiaCollo can help to provide a clearer picture of diachronic changes in the word's usage, in particular those related to semantic shift.

Distanbol analyses texts semantically. For this, it passes the input text to an Apache Stanbol web service that executes a NLP chain yielding named entities. This is followed by Entity Linking on the text. The resulting enhancements are rendered as human-readable HTML-page. In short, Distanbol is adding a human-readable rendering to the JSON-LD output produced by Stanbol.

The DTABf was developed in accordance with the P5-Guidelines of the Text Encoding Initiative (TEI). Since the TEI Guidelines are offering solutions for a huge amount of tagging requirements and are thus rather extensive and flexible, they are meant to be adjusted to the individual necessities of projects working with the TEI. For the DTA this was achieved by creation of the DTABf, a subset of the TEI/P5 tagset, which offers not only fixed sets of elements but also of corresponding attributes and (where applicable) values. The DTABf tagset is fully conformant with the TEI/P5-Guidelines, i.e. the TEI tagset was only reduced not extended in any way.

EXMARaLDA is a system for working with oral corpora on a computer. It consists of a transcription and annotation tool (Partitur-Editor), a tool for managing corpora (Corpus-Manager) and a query and analysis tool (EXAKT).

EXMARaLDA's features include, for instance:

• time-aligned transcription of digital audio or video
• flexible annotation for freely choosable categories,
• systematic documentation of a corpus through metadata
• flexible output of transcription data in various layouts and formats (notation, document)
• computer-assisted querying of transcription, annotation and metadata
• interoperable as it works XML based data formats that allow for data exchange with other tools (like Praat, ELAN, Transcriber etc.) and enable a flexible processing and sustainable usage of the data.

EXMARaLDA is used by researchers world wide in different contexts in which spoken language is analysed, these include:

• conversation and discourse analysis,
• study of language acquisition and multilingualism,
• phonetics and phonology,
• dialectology and sociolinguistics.

EXMARaLDA was developed in the project "Computer assisted methods for the creation and analysis of multilingual data" at the Collaborative Research Center "Multilingualism" (Sonderforschungsbereich "Mehrsprachigkeit" – SFB 538) at the University of Hamburg. Since July 2011, the development of EXMARaLDA is continued at the Hamburg Centre for Language Corpora, since November 2011 in cooperation with the Archive for Spoken German at the Institute for the German Language in Mannheim.

N-gram frequency list generation on FoLiA input.

Fowlt is an online, free-to-use context-sensitive English spelling checker. It follows the setup of the Dutch spelling checker Valkuil.net. Both Valkuil and Fowlt are unlike the typical spelling checkers: whereas the latter mostly try to find errors by comparing all words to a built-in dictionary and flag the word as an error if they can't find a match, Fowlt is context sensitive, taking into account the words around every word. Fowlt makes use of language models. These models are created by giving lots of texts to machine learning software (TiMBL and WOPR).

Fowlt is an online, free-to-use context-sensitive English spelling checker. It follows the setup of the Dutch spelling checker Valkuil.net. Both Valkuil and Fowlt are unlike the typical spelling checkers: whereas the latter mostly try to find errors by comparing all words to a built-in dictionary and flag the word as an error if they can't find a match, Fowlt is context sensitive, taking into account the words around every word. Fowlt makes use of language models. These models are created by giving lots of texts to machine learning software (TiMBL and WOPR).

Frog's current version will tokenize, tag, lemmatize, and morphologically segment word tokens in Dutch text files, will assign a dependency graph to each sentence, will identify the base phrase chunks in the sentence, and will attempt to find and label all named entities.

Frog's current version will tokenize, tag, lemmatize, and morphologically segment word tokens in Dutch text files, will assign a dependency graph to each sentence, will identify the base phrase chunks in the sentence, and will attempt to find and label all named entities.

Inkluz - detects foreign language inclusions in Polish texts.

Chunker for Polish. It recognises shallow syntactic structure (up to three levels) of phrases (chunks) in Polish texts.

KorAP is a new corpus analysis platform, optimized for large, multiple annotated corpora and complex search mechanisms.

            KorAP supports the query languages (of) COSMAS II, ANNIS, Poliqarp, Poliqarp+, CQL and FCQL.
            
            KorAP is developed at the Leibniz Institute for German Language in Mannheim. The individual modules are published as open source on GitHub.

KorAP is a new corpus analysis platform, optimized for large, multiple annotated corpora and complex search mechanisms.

            KorAP supports the query languages (of) COSMAS II, ANNIS, Poliqarp, Poliqarp+, CQL and FCQL.
            
            KorAP is developed at the Leibniz Institute for German Language in Mannheim. The individual modules are published as open source on GitHub.

The input file size is limited to 100kB.

Translates from->to:

Czech->English, Hindi, French, Russian, German

English->Russsian, German, Czech, Hindi, French

Russian->German, French, Czech, Hindi, English

German->Russian, Hindi, Czech, English, French

French->Russian, German, Czech, English, Hindi

Name Entity and Temporal Expression recognition

This is an experimental integration of a D4Science NLP processing service (NER Liner 2). This service identifies names of persons, locations, organizations, as well as money amounts, time and date expressions in Polish texts automatically.

A language dependency parser chain for Polish. The used tools include Morfeusz-2 with SGJP dictionary (for morphological analysis), wcrft2 (for tagging), and the MaltParser with a model for Polish. The CONLL output can be visualised with DepSVG, a dependency tree and predicate-argument structure visualizer.

Morphological analysis of Polish texts by Morfeusz 2 (based on the SGJP dictionary)

Morphological dictionary and tagger for the analysis of natural language texts in Polish.

Name Entity Recogniser for English by NLTK.

This is an experimental integration of a D4Science NLP processing service hub. This service runs a number of NER tools in parallel, and merges their results. It identifies names of persons, locations, organizations, as well as money amounts, time and date expressions -- and other expressions -- in English, French, Italian, Spanish and German texts automatically.

Oersetter is a Frisian-Dutch Machine Translation system.

Oersetter is a statistical machine translation (SMT) system for Frisian to Dutch and Dutch to Frisian. A parallel training corpus has been established, which has subsequently been used to automatically learn a phrase-based SMT model. The translation system is built around the open-source SMT software Moses.

Tokenizer for Dutch, English, German, French, Spanish and Italian. Consumes Plain text and produces TCF.

Keywords extraction for Polish by ReSpa based on the representation of text documents as word graphs.

Detection of semantic relations between Named Entities in Polish texts by Serel.

This is an experimental integration of a D4Science NLP processing service (spaCy). This service identifies performs dependency parsing for plain German text. For more information on spaCy, see https://spacy.io.

This is an experimental integration of a D4Science NLP processing service (spaCy). This service identifies performs dependency parsing for plain English text. For more information on spaCy, see https://spacy.io.

Recognition of spatial expressions in Polish texts.

Spejd - a partial, shallow parser for Polish with rule-based morphosyntactic disambiguation.