You may add text manually to the source window or by pasting.

Upon pasting, the text will be analyzed into segments in a preliminary form. This allows you to get an overview about how the input is structured before undergoing the processing selected (sentence-based lemmatization, analysis, translation, etc.). In addition you may modify the segmentation if necessary.

If the lines of the input text correspond to the segments to be treated further (irrespective of whether they show a corresponding punctuation mark at the end), please select the option 'Treat end of line as end of sentence' before entering the text into the source window.

This field displays translations for sentences that are similar to the sentence of the source window (and the first sentence there respectively, if the window contains a text).
The repository contains idiomatic expressions and frequently used phrases and application examples as well as certified translations of texts from various domains (translation memories). The repository is used in Lingenio's product series translate as well.

Translations are done with a statistical machine translation system instead of the rule-based system Lingenio normally uses. Thus, translations may differ from results in other panes.

We are constantly updating machine translation resources to improve translation quality and extend the range of languages.

Are you interested in a personalized statistical machine translator? Maybe one with a language pair that isn't yet listed here? Send a message to support@lingenio.de or use our contact form.

Research and Sponsoring

The Conjugator shows conjugation tables for the given verbs. Verbs can be entered either inflected or in their basic form.

The Glossary Maker searches the text for words satisfying the criteria specified by the Glossary Maker options. It looks up the dictionary entries for the corresponding basic forms (lemmata) and displays the set of results. The glossary follows the sentence structure of the text and the order of the words in the sentences such that for each sentence the corresponding information is displayed separately and can be inspected at a glance.

The glossary entries include indications about which reading of the word and which translation is most likely in the given context. The system computes this information from structural and semantic analyses of the sentences and higlights the corresponding suggestion in the entry by a yellow arrow. .

The language pair to be considered is selected by clicking on the flags in the source text window.

Currently, the Glossary maker options include search for specific parts of speech and exclusion of particular words (lemmata) called 'stopwords'. Other options like search for words of specific subject areas etc. will follow.

The function is being actively developed and improved, so please check back regularly for enhanced results.

The Annotation function has two different modes of operation:

Glossary

Annotations follow a user-defined glossary which is stored on the server.

Semantic

Annotations are defined by a list of semantic types.

The annotated parts are highlighted by their background-color. Hovering the mouse cursor over the highlighted text will display a popup containing the annotations.

The lemmatizer analyzes the input text token by token, maps the inflected forms onto the basic forms (lemmata) and returns the list of lemmata found together with information on frequency and part of speech classification.

Please note that word forms can refer to several word classes, for example plane may be verb or noun. If the option consider sentence structure is set, the lemmatizer uses syntactic sentence analysis in order to choose the contextually correct form. If consider sentence structure is not set, the lemmatizer just uses part of speech frequency and some few morphological constraints between tokens as a heuristics.

translateDict is the online version of the Lingenio offline product translateDict™ (cf. www.lingenio.de/en/products/dictionaries).
The dictionary uses the intelligent Lingenio search function FlexiFind © in order to find the contextually most appropriate translation.
Therefore it analyzes the expression entered in the source window (and the first sentence of a corresponding text respectively), detects the syntactically most important word and words the translation of which heavily depends on the main word, if any, then determines the translation(s) which fit best with respect to the context provided and highlights them in the corresponding dictionary entries displayed in the window.

The entries contain linguistic classifications of the words and inform about use conditions. The dictionaries from German to English or French include the official Duden explanations covering pronunciation, hyphenation and word definitions which Bibliographisches Institut GmbH kindly provides for the Lingenio dictionaries and translation systems.

You can learn more about our offline and online products and services covering various mono- and multilingual solutions on our services webpage and in our webshop.

Analysis

The analysis tool carries out structural analyses of the sentences introduced in the source text window. If the text consists of several sentences, the corresponding analyses are represented following the sequence of the sentences.

Depending on the options set the target window displays either the result of the syntactic analysis or more abstract and compact representations which are derived from these and focus on the semantically relevant relations and informations. Both types of analysis may be displayed in formal or informal notation. In addition, syntactic representations may be displayed in a format which follows the CoNLL standard.

Formal notation

Formal notation means that the structures are displayed as they are computed by the system. Please contact us if you are interested in APIs for integrating our analysis components in your software systems.

Informal notation

In informal notation the technical terms used for describing the relations between the nodes and the morphological, syntactic and semantic classifications are spelled out in terms of the surface language of the tool-window for better understanding.

CoNLL standard notation

The CoNLL option maps the syntactic representations to the structural format that has been suggested by the Conference on Natural Language Learning (CoNLL) for its series of shared tasks and beyond this as a kind of standard for syntactic annotations of corpora (cf. http://ifarm.nl/signll/conll, http://ilk.uvt.nl/conll/#dataformat). With respect to node descriptions and labels we use our own terms (as there are variants with respect to this anyway).

Please contact us if you are interested in obtaining annotations for larger texts or corpora.

Syntactic analysis

The syntactic analysis structures are slot grammar representations of the corresponding sentences. Slot grammar is a unification-based dependency grammar (cf. McCord 1989, http://www.lingenio.de/forschung/publikationen). It is used in Lingenio's Machine Translation systems and, for example, also in deep parsing of IBM Watson.
The structure displayed in the window represents a slot grammar tree rotated by 90 degrees to the left (such that the top is left and the leaf nodes, the lexical elements, are on the right). The visualization is structured into three columns where the first represents the tree structure as such with the names of the edges connecting the items, the second represents the stems of the words recognized and the pointers to the corresponding lexical entries (complemented by role filling information) and the third column shows the morpho-syntactic annotation of the words.

Semantic analysis

The representations of this level reduce the slot grammar analyses to the semantically relevant nodes and decorate these by information from the semantic lexicon. In addition they are the result of some structural standardizations which are suitable with respect to deep semantic analysis in later steps of processing. We call these structures slot grammar-based abstract dependency trees: SGaDTs).