Sap Se

Anton Snitko

Michail Vasiltschenko

Ralph Debusmann

Jens Scharnbacher

Slim Trabelsi

Benjamin Schork

Yvonne Miklosch

Jochen Geib

Iuliia Konstantinova

Tetyana Chernenko

Günther Fischer

Robert Stuehler

Klaus Heitlinger

Translation capability for language processing determines an existence of an abbreviation, followed by non-exact matching to map the abbreviation to the original full term. A received string in a source language is provided as input to a translation service. Translation proposals in a different target language are received back. A ruleset (considering factors, e.g., camel case format, the presence of a concluding period, and/or consecutive consonants) is applied to generate abbreviation candidates from the translation proposals. Non-exact matching (referencing e.g., a comparison metric) may then be used to map the abbreviation candidates to text strings of their original full terms. A mapping of the abbreviation to the text string of the original full term is stored in a translation database comprising linguistic data. Embodiments leverage existing resources (e.g., translation service, non-exact matching) to reduce effort and expense of accurately identifying abbreviations and then mapping them to their full original terms.

Detection of abbreviation and mapping to full original term

Techniques and solutions are described for translating strings in a human language that are associated with code, such as code that declares user interface elements in association with which the strings can be displayed. The strings can be embedded in code, or can be included in files that are accessed by the code or used in creating executable code. Strings can be extracted from data, such as files, received in a translation request. After translation, such as by a human translator or using automatic translation, the translation results can be provided in response to the translation request. The translation process can be automated, such that changes to files in a code repository can trigger a translation request. Disclosed technologies can facilitate the production of programs that are localized using different human languages.

String extraction and translation service

Disclosed herein are system, method, and computer program product embodiments for crawling feedback sources and generating a product improvement recommendation. In an embodiment, a Product Optimization Crawler and Monitor (POCM) system may crawl feedback comments from different sources such as an Internet source or a customer feedback database. The POCM system may apply artificial intelligence, natural language processing, and constraint modeling techniques to the feedback comments to identify product features as well as a feedback category corresponding to the product feature. The feedback category may include a positive, negative, or neutral feedback category. Using this information, the POCM system may generate a summary of the feedback from different sources and/or generate product improvement recommendation. The product improvement recommendation may include suggesting that a component from a first product be replaced with a similar component from a second product.

Product optimization crawler and monitor

Various examples are directed to systems and methods for identifying textual information regarding a first topic. A computer system may access a plurality of text units and detect that a first text unit of the plurality of text units is in a first language. The computer system may access a first language keyword set for the first topic, where the first language keyword set comprises a first plurality of keywords associated with the first language. The computer system may determine a first relevance score for the first text unit based at least in part on the first language keyword set. If the first relevance score is greater than a relevance score threshold, the computer system translates the first text unit to a base language and determines a text unit classification for the first text unit using a classification model trained with training data in the base language.

Computer systems for classifying multilingual text

Various embodiments of systems, computer program products, and methods to provide instant translation of user interfaces of a web application are described herein. In an aspect, a request is received to translate a user interfaces of a web application from a source language to a target language. A translatable user interface element associated with the user interface of the web application is determined. Further, the translatable user interface element is translated from the source language to the target language based on dynamic metadata associated with the translatable user interface element. The translated translatable user interface element in the user interface of the web application is rendered.

Growing community of inventors

Griesheim, Germany

Anton Snitko